Elastic Agent Builder for Enterprise Use Cases

Elastic Agent Builder
for Enterprise Use Cases

Build, deploy, and scale production-grade AI agents — from retrieval to orchestration — powered by the Elastic AI Search platform trusted at enterprise scale.

Ashish Tiwari
Principal Solutions Architect — Search Specialist

Platform Overview

The Elastic Search AI Platform

All Your Data, Real-Time, At Scale

Accelerate mission outcomes by finding insights from any data source

Any Data Source

Endpoints

Applications

Infrastructure

Services

Network/Security

›

Build Your Own

Elasticsearch

Out-of-the-Box

Observability

Out-of-the-Box

Security

Search AI Platform

Ingestion

Processing

Storage

Search

AI & ML

Visualization

🔄Automation

Search AI Lake

Self-Managed

Full control on your infrastructure

Elastic Cloud

Managed service on AWS, GCP, Azure

Serverless

Zero ops, automatic scaling

›

Outcomes

Dashboards

Integrations

Orchestration

Workflows

One Platform

Search, Observability, and Security unified on a single data layer

Any Deployment

Self-managed, cloud-hosted, or fully serverless — your choice

Real-Time Insights

From ingestion to action in milliseconds, at petabyte scale

Search Maturity — From Keywords to Agents

The Search Maturity Model

Search didn't jump from keywords to AI. It evolved in five distinct stages — each solving the limitations of the last.

Stage 1

Keyword Search

BM25 / TF-IDF

Exact term matching. Fast and predictable. The foundation of web search for 20+ years.

Limitation

No understanding of meaning. "automobile" won't find "car". Vocabulary mismatch kills recall.

Stage 2

Semantic Search

Dense Vectors / kNN

Embedding models encode meaning into vectors. "car" and "automobile" land nearby. Understands intent, not just words.

Limitation

Loses precision on exact terms, names, codes. Struggles with structured or boolean queries.

Stage 3

Hybrid Search

BM25 + Vector + ELSER + RRF

Best of both worlds. Fuses keyword precision with semantic recall. ELSER adds learned sparse representations. RRF merges rankings.

Limitation

Returns documents, not answers. Users still read and synthesize results manually.

↓

Stage 4

Conversational RAG

LLM + Retrieval + Memory

LLM generates answers grounded in retrieved context. Conversational memory rewrites follow-ups. Users get answers, not links.

Limitation

Read-only. Can answer questions but can't take actions, call APIs, or chain multi-step workflows.

Stage 5

Agentic AI

Agents + Tools + MCP/A2A

Agents reason, plan, and act. Retrieve context, call tools, delegate to other agents, execute multi-step workflows autonomously.

Current frontier

Requires robust retrieval, tool orchestration, guardrails, and observability. This is where Elastic plays.

Key insight: Each stage builds on the previous — you can't skip steps. Agentic AI without solid retrieval is just expensive hallucination. The maturity model is cumulative, not a replacement.

Playground — No-Code RAG Prototyping

Elastic Playground

UI for building and testing RAG applications without writing code.

Core Modes

Chat mode — conversations with context retrieval
Query mode — test and refine ES queries

LLM Flexibility

Elastic Managed inference
OpenAI, Bedrock, Azure, local
Swap models per iteration

Advanced Features

View & modify ES queries in real-time
Export Python code for your app
A/B test models & retrieval strategies

Memory & Context

Conversational memory rewrites follow-ups
Session state across turns
No manual prompt engineering

Requirements

Elasticsearch v8.14+, one index with data, LLM provider credentials (Elastic, OpenAI, Bedrock, Azure, or local)

Agent Builder

Build, connect, and expose intelligent agents — all from a single platform.

The Problem — Why Agents Fail

Most Agents Break After Three Turns

The bottleneck is never the model. It's always the context.

LLMs can reason. They can't remember.
Stuffing 200k tokens into a prompt isn't a strategy
Agents need the right context at the right time
Retrieval isn't a feature — it's the foundation
Without search, your agent is expensive autocomplete

Multi-agent LLM systems fail at 41-86.7% rates in production — orq.ai

Context rot: accuracy decreases as context length increases — inkeep.com

Cascading failures where single root-cause error propagates — atla-ai.com

              // what most "agents" look like today

              while (true) {

                const response = await llm(

                  `${entire_knowledge_base}` +

                  `${all_chat_history}` +

                  `${user_message}`

                )

                // $4.20 per turn

                // 12 second latency

                // still hallucinates

              }

Architecture — How It All Connects

Elastic Agent Builder: Build Once. Connect Everywhere.

Chat Integrations via MCP → Tools. Custom Agents via API/A2A → Agents. Native Chat Experience → Elastic UI. All on the Elasticsearch Platform.

Agent Builder — Core Components

Chat + Agents + Tools

Chat

Interactive playground to test & iterate. Connect an index, pick a model, test retrieval.

Agents

Custom LLM instructions + toolsets. Define behavior, assign tools, set guardrails.

Tools

Actions your agent can take — built-in Elastic tools, custom tools, or MCP imports.

Tool Types

ES|QL Tools

Pre-defined queries with parameterized inputs

Index Search

LLM dynamically constructs queries

MCP Tools

Connect external MCP servers

Workflow Tools

Orchestrated multi-step actions

POST Register a Tool

POST /api/agent_builder/tools
{
  "id": "find_client_exposure",
  "type": "esql",
  "description": "Finds client portfolio
    exposure to negative news",
  "configuration": {
    "query": "FROM news_index | ..."
  }
}

POST Create a Custom Agent

POST /api/agent_builder/agents
{
  "id": "financial_assistant",
  "name": "Financial Assistant",
  "instructions": "You are a
    specialized data assistant...",
  "tools": [
    "find_client_exposure"
  ]
}

POST Converse with Your Agent

POST /api/agent_builder/converse
{
  "agent_id": "financial_assistant",
  "input": "Which clients are
    most at risk from bad news
    this week?",
  "conversation_id": "..."
}

① Register Tool → ② Create Agent → ③ Converse

MCP Connector — Extend Your Agent's Toolbox

Import Any MCP Tool Into Your Agent

MCP Ecosystem

GitHub

Confluence

PagerDuty

Slack

Jira

Any MCP

listTools

MCP Connector

Kibana Stack Management

Auto-Discovery Auth Built-in

callTool

Your Elastic Agent

Agent Builder

Tools Guardrails

How It Works

Stack Management → Connectors → New MCP
Point to any remote MCP server URL + auth
Auto-discovers tools via listTools
Assign discovered tools to any agent

What This Unlocks

Incident management via PagerDuty MCP
Code search & PRs via GitHub MCP
Messaging via Slack, Teams MCP
Knowledge bases via Confluence, Notion MCP

Bidirectional Power

Elastic serves its own tools as an MCP server
Claude, Cursor, Copilot can call Elastic tools
Cross-platform agent-to-agent orchestration
Any MCP client gets Elastic search + security

Native Automation — Elastic Workflows TECH PREVIEW

Elastic Workflows

Native automation engine that combines predictable execution with AI agent reasoning — directly where your data lives.

Triggers

Elastic Alerts

⏰ Schedule / Cron

▶️ Manual Run

Agent Builder

Workflow Engine

🔀

Conditions

if / else branching

🔄

Loops

for-each iteration

AI Prompts

LLM reasoning steps

HTTP Steps

Call any API

ES Search

Query & index data

Cases

Case management

Defined in YAML — platform handles execution

Actions

💬 Slack Messages

🎫 Jira Tickets

PagerDuty

📧 Email / Notify

Any API / Service

Agent + Workflow Integration

Add any workflow as a tool in Agent Builder. Agents invoke workflows based on user intent — combining AI reasoning with deterministic, repeatable execution. No integration gap between reasoning and action.

Why This Matters

Agents reason. Workflows execute. Together: restart a service, update a record, send a notification, triage an alert — all from a single conversation. Automation where your data lives.

Interoperability — MCP, A2A & REST API

Build Once. Expose Everywhere.

Your Elastic Agent connects to the world through three protocols — each optimized for a different integration pattern.

MCP

ELASTIC

Agent Builder

💬
Claude

⌨️
Cursor

VS Code

LangChain

Dev Tools & AI Assistants — tools available where developers already work

A2A

ELASTIC

Agent Builder

🌐
Gemini

Strands

🏢
MS Foundry

🤝
Any Agent

Agent-to-Agent — peer collaboration, delegation, not just tool calls

REST

ELASTIC

Agent Builder

📱
Apps

Backend

🔄
CI/CD

Workflows

Custom Integrations — embed in any app, workflow, or pipeline

Architecture Patterns — What You Can Build

Three Patterns. One Platform.

Start simple. Evolve as your use case demands. The same retrieval and inference stack powers all three.

Pattern 1

Simple RAG

User asks a question → retrieve context → LLM generates grounded answer.

User Query

↓

Hybrid Search + Rerank

↓

LLM → Answer

Use: Docs Q&A, knowledge base, support chatbot

Pattern 2

Agentic RAG

Agent reasons about the query → decides which tools to call → retrieves, acts, responds.

User Query

↓

Agent → Reason + Plan

↓

Search

ES|QL

MCP

↓

Response + Citations

Use: IT ops, incident triage, compliance research

Pattern 3

Multi-Agent (A2A)

Orchestrator delegates to specialist agents via A2A. Each agent owns a domain.

User Query

↓

Orchestrator Agent

↙

↓

↘

Search Agent

Analytics Agent

Action Agent

Use: Enterprise workflows, cross-domain automation

Progressive complexity: Start with Pattern 1 in Playground today. Graduate to Pattern 2 with Agent Builder + Tools. Scale to Pattern 3 with A2A. Same platform, same data, same security model throughout.

Elastic Inference Service

One API. Every model. Fully managed, GPU-accelerated inference.

Model Catalog — Elastic Inference Service (/_inference)

One API. Every Model You Need (/_inference)

Fully managed, GPU-accelerated. Swap models per step. Unified inference API across all providers.

Anthropic

Claude Opus 4.6 Claude Opus 4.5 Claude Sonnet 4.6

O OpenAI

GPT-5.2 GPT-4.1 GPT-4.1 Mini GPT-OSS-120B

Google

Gemini 2.5 Pro Gemini 2.5 Flash

Native on Elastic

Jina AI

Jina v5 small Jina v5 nano Jina v3 Reranker v3 Reranker v2

Native

ELSER (Sparse) E5 Multilingual

Third-Party & BYO

Microsoft Alibaba ONNX / PyTorch Custom Models

Register & Use Any Model

          PUT _inference/chat_completion/my-openai-endpoint
{
  "service": "elastic",
  "service_settings": {
    "model_id": "openai-gpt-4.1"
  }
}
        

Embeddings — Jina v5 on Elastic Inference

Jina SOTA Multilingual Embeddings. Native on Elastic.

v5-text-small — 677M params

Highest scoring multilingual model under 1B parameters. Matches jina-v4 (3.8B) at 5.6x smaller.

MTEB English v271.7

71.7

MMTEB Multilingual67.7

67.7

Retrieval Avg (5 benchmarks)63.28

63.28

v5-text-nano — 239M params

Matches all sub-500M models including KaLM-mini-v2.5 (494M).

MTEB English v271.0

71.0

MMTEB Multilingual65.5

65.5

Why This Matters

5.6x smaller than v4 — same quality
Native on EIS — zero infra setup
GPU-accelerated, fully managed, auto-scaling
Multilingual out of the box
Works with vector search and hybrid search

Setup — 4 Lines

              PUT _inference/text_embedding/jina-v5
{
  "service": "elastic",
  "service_settings": {
    "model_id":
      "jina-embeddings-v5-text-small"
  }
}
            

The Missing Piece — Why Context Is Everything

An Agent Without Context
Is Just Expensive Guesswork

Every use case we just covered depends on one thing: getting the right information to the agent at the right time. That's not a model problem. That's a search problem.

💸

Without Context

Stuffing 200k tokens. $4+ per turn. 12s latency. Still hallucinates.

With Context Engineering

Right docs, right time. Sub-second retrieval. Grounded answers with citations.

Context Engineering

The right information, at the right time — powered by Elastic search.

Context Engineering — Elastic Provides Everything You Need

Elastic Provides Everything You Need

Context Engineering — from data prep to retrieval to agentic AI to evaluation

Data Prep & Inference

Sparse & dense vector encoding models
Multi-lingual embedding models
Multi-modal embedding models
GPU-based inference service
Automatic chunking
200+ connectors
Web crawlers
Automated parsing
Quantization

Retrieval

Vector search
Lexical search
Hybrid search
Geospatial search
Filtering & faceting
Reranking models
Learning to rank (LTR)
Query rules & rescoring
Query understanding models
RAG Workflows
LLM integration

Agentic AI

Tool building
Agentic workflows
Tool selection
Memory systems
Prompt management
MCP/Agent interfaces

Evaluation & Monitoring

Relevance benchmarking
A/B testing
Behavioral analytics
Cost & token tracking
Query logging, metrics, tracing

Vector DB — Elasticsearch

The foundation powering all four pillars — storing vectors, documents, and metadata at petabyte scale

Search Relevance

Search Relevance Pyramid

Retrievers API

Retrievers API — Making Multi-Stage Query Easy

Compose retrieval, rescoring, and reranking in a single POST /_search request — fully nested, fully composable.

ES|QL — Piped Query Language

Query Your Data Without the JSON Pain

ES|QL is Elastic's piped query language — familiar syntax, powerful transforms, and native integration across the entire stack.

Before — JSON Query DSL

            POST logs-*/_search

            {

              "query": {

                "bool": {

                  "filter": [

                    { "term": { "status": "error" }},

                    { "range": { "@timestamp": {

                      "gte": "now-24h"

                    }}}

                  ]

                }

              },

              "aggs": { "by_service": {

                "terms": { "field": "service.name" }

              }}

            }

After — ES|QL

            FROM logs-*

            | WHERE status == "error"

              AND @timestamp > now() - 24 hours

            | STATS count = COUNT(*)

              BY service.name

            | SORT count DESC

3 lines vs 18 lines. Same result. Readable by anyone.

Agent Builder

ES|QL tools for agents

Alerting

Detection rules in ES|QL

Dashboards

Lens + ES|QL panels

Workflows

Query steps in automation

Security — Access Control in Agent Builder

Two Layers of Access Control

Control what agents can do through tool assignment, and what data users can see through Elasticsearch security — two independent layers working together.

Layer 1 — Agent Builder

Tool-Based Access Control

Agents only access the tools assigned to them. No tool = no access to that data or action. Many-to-many relationship.

Finance Agent

HR Agent

IT Ops Agent

──────

Revenue Search Tool

Employee Data Tool

Logs ES|QL Tool

✓ Assign tools per agent — each agent only sees its assigned tools

✓ Many-to-many — one tool can serve multiple agents, one agent can use many tools

✓ Admin controls — decide which users can create or manage tools

Layer 2 — Data Search

Index / Field / Document Security

When a tool queries Elasticsearch, the data-layer security kicks in — filtering results based on user roles and permissions.

Index-Level

Control which indices each role can access — finance_read vs hr_admin see different index sets

Field-Level

Hide sensitive fields (SSN, salary, PII) from specific roles — even within the same index

Document-Level

Filter individual documents per user with query-based rules — same search, different results

How they work together: An agent can only call its assigned tools (Layer 1). When a tool runs a search, Elasticsearch enforces index/field/document-level permissions for that user (Layer 2). Two independent layers — no single point of bypass.

Vibe Coding with Elastic

Describe what you want in natural language — Agent Skills handle the rest.

Agent Skills — SKILL.md Open Standard

Turn AI Agents Into Elastic Experts

What is SKILL.md?

The open agentskills.io standard. Each skill is a folder with a SKILL.md file — structured metadata + instructions. When an AI agent reads it, it learns how to perform Elastic tasks correctly — right APIs, right patterns, right guardrails.

26 Skills Available

Elasticsearch — Search, indexing, ES|QL, auth, audit, file-ingest, troubleshooting
Kibana — Agent-builder, alerting, audit, connectors, dashboards, streams, vega
Observability — LLM-obs, logs-search, SLOs, service-health
Security — Alert triage, case mgmt, detection rules, sample data
Cloud — Access mgmt, create/manage projects, network security, setup

Works With

Elastic Agent Skills — CLI install flow showing 26 skills and GitHub repo

Vibe Coding — Build With Natural Language

What You Can Build With Vibe Coding + Elastic Skills

Describe what you want in plain English. Elastic Agent Skills handle the rest — correct APIs, correct config, correct best practices.

"Build me a hybrid search API"

Creates index mapping, sets up ELSER, configures hybrid search with RRF, writes API endpoint — following Elastic best practices.

Search

"Create an APM dashboard"

Builds full observability dashboard — service maps, latency charts, error panels, SLO tracking. Correct APIs, correct JSON.

Observability

"Set up brute force detection"

Creates EQL/ES|QL detection rules, configures alert actions, sets severity and risk scoring correctly.

Security

"Build a RAG agent for our docs"

Sets up ingestion, creates vector index, configures inference, builds agent in Agent Builder — end-to-end in one conversation.

Agent Builder

"Why is my cluster yellow?"

Checks shard allocation, identifies unassigned shards, diagnoses root cause, applies fix — all through correct ES APIs.

Ops

"Ingest my Kafka logs"

Configures Fleet integration, sets up ingest pipelines with grok processors, creates index templates, verifies data flow.

Ingestion

github.com/elastic/agent-skills — Open source. Apache 2.0. Contribute your own.

Industry Use Cases — Regulated & High-Compliance

Agents for Regulated Industries

Where compliance is non-negotiable. Elastic gives you data sovereignty, audit trails, and granular access control out of the box.

BFSI

Fraud investigation — transaction patterns + compliance rules via hybrid search
KYC document retrieval — scanned docs in minutes, not days
Compliance Q&A with citations and audit trails

Hybrid Search Audit Trail

Public Sector

Citizen services — navigate permits, benefits in plain language
Policy research — legislation via hybrid search, not keyword
On-prem, air-gapped, FedRAMP-ready deployment

On-Prem Air-Gapped

Healthcare

Clinical decision support — indexed medical literature with citations
Document-level security for HIPAA compliance
Risk assessment with ES|QL aggregations

HIPAA DLS

Key differentiator: Data-layer security (index/field/document level), on-prem deployment, auditable retrieval trails. Your data stays where compliance requires.

Industry Use Cases — Commercial & Digital

Agents for Every Business

From IT help desks to shopping assistants — the same platform scales across every commercial use case.

Mid-Market

IT support — resolves L1/L2 from runbooks + past resolutions
HR policy assistant — multi-language via Jina v5
Incident response — correlates logs, metrics, traces automatically

IT Ops HR

Digital Natives

Developer docs agent — search by intent, get right code snippet
In-product search — users self-serve via REST API or MCP
Log analysis — "why did deploy-42 fail?" with ES|QL

DevEx MCP

E-Commerce

Shopping assistant — semantic intent + price filters in one query
Personalization — behavioral signals + product vectors
Returns & support — multi-language, MCP-connected logistics

Semantic Vectors

200+ connectors — Confluence, SharePoint, Google Drive, ServiceNow, Salesforce. Federate all your data through one agent.

Observability — Monitor Your Agents in Production

LLM & Agent Observability — Built In, Not Bolted On

Your agents are only as good as your ability to monitor them. Elastic gives you full-stack observability for every agent interaction.

Trace Every Interaction

End-to-end trace spans for each agent turn
Tool invocations, retrieval calls, LLM requests
Latency breakdown per step
Error propagation and root cause analysis

Cost & Token Tracking

Input/output tokens per request
Cost per conversation and per user
Model comparison (cost vs. quality)
Budget alerts and anomaly detection

Quality & Safety

Retrieval relevance scoring
Hallucination detection signals
User feedback loops (thumbs up/down)
Guardrail trigger monitoring

⏱

Latency

Per-step & end-to-end response time

💰

Cost

Token usage & spend per conversation

🎯

Relevance

Retrieval quality & reranking scores

🛡

Safety

Guardrail triggers & hallucination signals

Why this matters: Most agent platforms require third-party tools for monitoring. With Elastic, your agents run on the same platform you already use for logs, metrics, traces, and APM — zero integration gap.

Federated Search

Query everywhere. Move nothing. Data stays where it belongs.

Federated Search — Agent Builder + MCP

Query Any Source. Store Nothing.

Agent Builder uses MCP connectors to query external data sources in real time — data stays at the source, sovereignty-compliant by design.

MCP Federation

Query at source — zero data movement. Sovereignty-compliant. Always fresh, no sync lag. Source retains access control.

200+ Connectors

Ingest into Elastic for hybrid search, ML, and analytics. Incremental sync, DLS built-in, auto chunking + embedding.

Use Both Together

Federate when compliance prevents data movement. Ingest when you need search + ML. Combine for maximum coverage.

Elastic Connectors — 200+ Integrations

Ingest or Federate. Your Choice.

When you need data in Elastic for search, analytics, or ML — 200+ connectors handle ingestion. When sovereignty says no, MCP federates instead.

Native Connectors (Data → Elastic)

Sync data into Elasticsearch indices for hybrid search, analytics, and ML. Full text + vector + sparse vector support.

Cloud Storage

S3, Azure Blob, GCS, Dropbox, Box, OneDrive

Databases

PostgreSQL, MySQL, MongoDB, Oracle, SQL Server

SaaS Apps

Salesforce, ServiceNow, Jira, Confluence, Slack

Content & Docs

SharePoint, Google Drive, Notion, GitHub, Web Crawler

Incremental sync — only changed docs
Access control sync (DLS) built in
Auto chunking + embedding for vector search

MCP Federation (Query at Source)

Agent Builder queries external systems in real time via MCP protocol. Data never enters Elastic.

CRM / ERP

Salesforce, SAP, HubSpot, Dynamics 365

IT Operations

PagerDuty, ServiceNow, Jira, GitHub

Databases

PostgreSQL, MySQL, Snowflake, BigQuery

Communication

Slack, Teams, Email, Custom APIs

No data movement — sovereign-compliant
Always fresh — no sync lag
Source retains its own access control

Choose connectors when you need hybrid search, ML, or analytics on the data. Choose MCP when sovereignty, freshness, or compliance prevents data movement. Use both together for maximum coverage.

Cross-Cluster Search — Elastic to Elastic

One Query. Every Cluster. Every Region.

CCS sends queries to remote Elastic clusters and merges results at the coordinator. Raw data never leaves its home cluster.

Native Protocol

Zero translation overhead between clusters
Full Query DSL + ES|QL support
Aggregations compute locally, merge at hub
CCR available for read replicas when needed

Security at Every Layer

Each cluster enforces its own DLS/FLS
API keys scoped per cluster per role
TLS encryption in transit between clusters
Full audit logging at every node

Sovereignty by Design

Raw data never leaves the source cluster
Only doc IDs + scores return to coordinator
Each region operates independently
Central orchestration, distributed execution

Federated Search — Connector Integration

Chat With Your Entire Ecosystem

Coming in

Elastic 9.4

Use Cases

From document search to call analysis — see the platform in action.

Use Case — Central Document Intelligence

Central Document Search & Chat

01 · DATA SOURCES

SharePoint · Confluence · S3 · Databases · APIs

200+ Elastic Connectors — ingest from anywhere

↓

02 · CHUNK & EMBED

semantic_text — zero pipeline code

Auto-chunk + embed via EIS (ELSER · OpenAI · Google · HuggingFace)

↓

03 · VECTOR STORE

DiskBBQ + HNSW — 32× memory savings

float→int4 quantized · BM25 + kNN + RRF hybrid search

↓

04 · AGENT BUILDER

Conversational RAG with citations

Intent routing · semantic reranking · inline citations · guardrails + DLS/FLS

Enterprise Document Agent LIVE

What is our refund policy for enterprise contracts?

Per Policy-ENT-2024-07, enterprise contracts allow pro-rata refunds within 30 days of renewal. Requires VP approval for amounts over $50K. [§3.2] [§5.1]

Compare onboarding SLAs across regions

APAC: 5 business days. EMEA: 7 business days. Americas: 3 business days. [SLA Doc v4.1]

Find all docs mentioning GDPR data retention

Found 23 documents across Confluence, SharePoint, and Legal S3. Top match: Data-Governance-EU.pdf — retention capped at 36 months. [Art. 17] [Art. 5(1)(e)]

Searching 48,000 documents across 12 sources...

Use Case — Visual Intelligence

Image Search & Visual Recognition

01 · INGEST & OCR

Product images · Camera feeds · Scanned docs

OCR text extraction + EXIF metadata + preprocessing

↓

02 · VISION EMBEDDINGS

CLIP · SigLIP · ArcFace (external)

Image vectors + face vectors — run outside EIS

↓

03 · STORE & INDEX

DiskBBQ + HNSW — 32× memory savings

Image vectors · face vectors · OCR text · EXIF metadata

↓

04 · SEARCH CAPABILITIES

kNN similarity · ColPali late-interaction ranking

Reverse image search · face matching · metadata pre-filter · OCR hybrid fallback

Visual Search Agent LIVE

Find similar products to this shoe image

kNN visual similarity → Found 8 matches:
1. Nike Air Max 90 — 97.2%
2. Adidas Ultraboost — 94.1%
3. Puma RS-X — 91.8%

Filter to red colorway under ₹5,000

metadata pre-filter + kNN →
1. Puma RS-X Red — 91.8% · ₹4,299
2. Campus Flash Red — 88.4% · ₹2,999

Search this scanned invoice for total amount

ColPali late-interaction + OCR →
Total: ₹1,24,500 · Vendor: Reliance Digital · Date: 12-Mar-2025. MaxSim score: 0.94

Processing image embeddings...

Use Case — Customer Call Intelligence

Customer Support Call Analysis

01 · AUDIO INPUT

Customer call recordings

Support calls, sales calls, video meetings

↓

02 · SPEECH → TEXT

Whisper model via EIS

Speaker diarization + timestamp alignment

↓

03 · CHUNK & EMBED

semantic_text — auto-chunk transcripts

Generate e5 embeddings + sentiment + entity extraction

↓

04 · STORE IN ELASTIC

DiskBBQ + HNSW — 32× memory savings

Text vectors + metadata + compliance flags + sentiment scores

↓

05 · HYBRID SEARCH

BM25 + kNN + RRF on Elastic

Semantic reranking · cross-call aggregation · trend surfacing

Call Analysis Agent LIVE

Why was customer on call #4821 disappointed?

Customer escalated twice. Sentiment: negative (0.18). Root cause: promised callback in 2hrs, actual callback after 26hrs. Agent failed to log the commitment. [00:04:12–00:06:45]

Show me common frustration patterns this week

Analyzed 842 calls this week:
1. Long hold times — 31% of negative calls
2. Repeated issue explanation — 24%
3. Unresolved billing disputes — 19%

Which agents need coaching on empathy?

3 agents below empathy threshold:
Agent Priya K. — avg sentiment 0.22 · 6 escalations
Agent Rahul M. — avg sentiment 0.29 · 4 escalations
Based on tone analysis + customer feedback scores

Analyzing 3,400 call transcripts via hybrid search...

Competitive Analysis — How Elastic Compares

Competitive Landscape

Elastic is the only platform combining search, observability, security, and agent builder with native MCP/A2A support.

Capability	Elastic	Pinecone / Weaviate	MongoDB Atlas	OpenSearch
Hybrid Search (BM25+Vector+Sparse)	Native	~ Limited	~ Basic	~ Partial
Learned Sparse (ELSER)	Built-in	No	No	No
Agent Builder + Playground	GA	No	No	No
MCP + A2A Support	Native	No	No	No
Agent Skills (Open Standard)	26 skills	No	No	No
Managed Model Catalog (EIS)	Full	~ Limited	~ Some	~ Basic
200+ Data Connectors	Yes	Few	~ Some	~ Fork lag
Observability + Security	Unified	No	No	~ Limited

Why Elastic — One Platform, Three Superpowers

One Platform. Three Superpowers.

Search

Hybrid retrieval, model catalog, Jina v5, ELSER. Your agent's knowledge layer.

Observe

Logs, metrics, traces, APM. Monitor agents in production.

Protect

SIEM, endpoint, SOAR. Document-level security. Compliance built in.

Build Something Today

Elastic Cloud

14-day free trial. Agent Builder included. Playground for no-code prototyping.

Agent Skills

Install 26 Elastic skills in Claude Code, Cursor, or any agent.

npx @anthropic/skills install elastic

Docs & Community

Quick-start guides, GitHub repos, Elastic Community Slack, Search Labs.

The best agent is the one
your users actually trust.

That starts with the right context, at the right time, from a platform you can inspect, control, and extend.

Resources

→ elastic.co/elasticsearch/agent-builder → elastic.co/search-labs → github.com/elastic/elasticsearch-labs → github.com/elastic/agent-skills → elastic.co/docs/explore-analyze/workflows

Elastic Agent Builderfor Enterprise Use Cases

The Elastic Search AI Platform

One Platform

Any Deployment

Real-Time Insights

The Search Maturity Model

Keyword Search

Semantic Search

Hybrid Search

Conversational RAG

Agentic AI

Elastic Playground

Core Modes

LLM Flexibility

Advanced Features

Memory & Context

Requirements

Agent Builder

Most Agents Break After Three Turns

Elastic Agent Builder: Build Once. Connect Everywhere.

Chat + Agents + Tools

Chat

Agents

Tools

Tool Types

Import Any MCP Tool Into Your Agent

How It Works

What This Unlocks

Bidirectional Power

Elastic Workflows

Agent + Workflow Integration

Why This Matters

Build Once. Expose Everywhere.

Three Patterns. One Platform.

Simple RAG

Agentic RAG

Multi-Agent (A2A)

Elastic Inference Service

One API. Every Model You Need (/_inference)

Register & Use Any Model

Jina SOTA Multilingual Embeddings. Native on Elastic.

v5-text-small — 677M params

v5-text-nano — 239M params

Why This Matters

Setup — 4 Lines

An Agent Without ContextIs Just Expensive Guesswork

Without Context

With Context Engineering

Context Engineering

Elastic Provides Everything You Need

Data Prep & Inference

Retrieval

Agentic AI

Evaluation & Monitoring

Search Relevance Pyramid

Retrievers API — Making Multi-Stage Query Easy

Query Your Data Without the JSON Pain

Before — JSON Query DSL

After — ES|QL

Two Layers of Access Control

Tool-Based Access Control

Index / Field / Document Security

Vibe Coding with Elastic

Turn AI Agents Into Elastic Experts

What is SKILL.md?

26 Skills Available

Works With

What You Can Build With Vibe Coding + Elastic Skills

"Build me a hybrid search API"

"Create an APM dashboard"

"Set up brute force detection"

"Build a RAG agent for our docs"

"Why is my cluster yellow?"

"Ingest my Kafka logs"

Agents for Regulated Industries

BFSI

Public Sector

Healthcare

Agents for Every Business

Mid-Market

Elastic Agent Builder
for Enterprise Use Cases

An Agent Without Context
Is Just Expensive Guesswork

The best agent is the one
your users actually trust.