✨ The first-ever highly technical conference on Agentic Engineering ✨

Agent EngineeringConference 2026

Name: AgentEng 2026 - Agent Engineering Conference
Location: London

The Engineering Discipline Behind Agentic AI

Learn how teams build and operate agentic systems with robust context engineering, harnesses, evals, orchestration, memory, and guardrails.

⚡Founders Edition · Limited spaces

London (Summer 2026)

Next stop: San Francisco (Fall 2026)

Become a Sponsor

Tickets are not on sale yet. Join the waitlist for launch updates and early access announcements.

FOUNDERS EDITION

For practitioners building production AI agents

Calls open: speakers + sponsorships · tickets waitlist

orchestrator

Initializing agent...

>cat README.md

What is Agent Engineering Conference?

// definition

Agent Engineering is the discipline of designing, evaluating, and orchestrating non-deterministic AI systems using explicit specification, feedback loops, and operational guardrails.

AgentEng (Agent Engineering Conference) is the first conference dedicated solely to the engineering disciplines behind Agentic AI, from intelligent specification and strategic orchestration to evaluation, memory, and context.

We focus on what actually works in production. Real constraints. Real tradeoffs. Real systems.

We bring together practitioners building production-grade agentic systems to define how AI agents are designed, operated, orchestrated and scaled.

Backed by 2,000+ builders from the London Agentic AI community

$ agenteng --list-disciplines

Code

Context

Evaluation

Orchestration

Memory

spec-agent

Initializing agent...

From Prompt Engineering to Agent Engineering

AI system engineering keeps specializing in production. In practice, these disciplines converge in one place: Agent Engineering.

discipline::01

Prompt Engineering

discipline::02

Context Engineering

discipline::03

Harness Engineering

discipline::04

Eval Engineering

discipline::05

Memory Engineering

discipline::06

Skills Engineering

discipline::07

Guardrail Engineering

discipline::∞

*.Engineering

convergence::active

Agent Engineering

Context, evals, memory, harnesses, skills, guardrails, and orchestration converge in production systems engineering.

$ all_roads --lead-to agent_engineering

Prompt Engineering

Context Engineering

Harness Engineering

Eval Engineering

Memory Engineering

Skills Engineering

Guardrail Engineering

discipline::∞

... *.Engineering

convergence::result

Agent Engineering

Production agentic systems require more than prompt engineering. They depend on context, harnesses, evals, memory, skills, and guardrails working together as one engineering discipline.

AgentEng London · Summer 2026

Join us in the heart of London for the first conference dedicated solely to engineering agentic AI systems.

Day

300+

Attendees

15+

Speakers

London → San Francisco → Global

Venue details coming soon

>Next stop: San Francisco

venue-locator

Initializing agent...

The Agent Engineering Manifesto

Models don't read minds. Agent engineering is the discipline of specifying, designing, building, and orchestrating intelligent systems.

Building Agentic AI for production is fundamentally different from traditional software. Every input is an edge case. As foundation models become more capable and increasingly commoditized, the real differentiator shifts to Agent Engineering, the discipline of designing, operating, and orchestrating non-deterministic Agentic AI systems reliably.

Agentic AI emerges when engineering decisions around context, memory, evaluation, orchestration, and tooling and infrastructure are intentionally designed as a modular, future-proof system.

Intelligent specification, human-in-the-loop oversight, and strategic orchestration are foundational.

AgentEng exists to define, share, and advance the engineering behind Agentic AI.

manifesto-reader

Initializing agent...

The Agent Engineering Mindset

Non-Determinism

Agentic AI doesn't conform to software reliability. Embrace unpredictability as a feature, not a flaw.

Intelligent Specification

Models won't read minds. Clear specs are foundational. Better planning yields better agents.

Every Input is an Edge Case

Users can ask anything. Traditional testing fails. Ship to learn, not to be perfect.

Strategic Orchestration

Allocating compute, liquidity, and human review efficiently is critical. Manage resources at scale.

The Reviewer Framework

Engineering the transition from writing code to architecting agentic reviewers. Focus on validation loops and automated PR gates.

Agent Networking

Agents must communicate intelligently. Parallel and sequential workflows prevent conflicts and overlap.

Core Engineering Themes

These engineering disciplines form the backbone of production-grade Agentic AI systems.

>agenteng --themes --list

🧩

Code Engineering

How agents write, modify, and reason over code. Explores autonomous coding systems, IDE-native agents, and agent-driven refactoring workflows.

🧪

Eval Engineering

How we measure agent behavior in non-deterministic systems. Covers evaluation frameworks, behavioral testing, and reliability guardrails.

🧠

Memory Engineering

How agents store, retrieve, and evolve state over time. Covers short-term vs long-term memory, retrieval strategies, and personalization.

🧭

Context & Skills Engineering

The art and science of shaping what an agent sees at runtime. Includes MCP (Model Context Protocol), context construction, compression, and grounding techniques.

🧰

Harness Engineering

Defines the execution environment around an agent. Wires models to tools, policies, sandboxes, and execution constraints.

🔗

Multi-Agent Engineering

Focuses on collaboration between agents. Covers communication protocols, task decomposition, and coordination strategies.

themes-engine

Initializing agent...

Advanced Program Tracks

These sessions go deeper into emerging and forward-looking areas of Agent Engineering.

--optimize

Agent Optimization

Automatically Optimze agents across all layers prompts, RAG,Protocols, memory and context.

--design-ax

Agent Experience (AX)

Designing machine-readable interfaces, environments, and feedback loops that shape Agent Experience.

--future-code

Agentic Coding

How software development evolves as agents become first-class contributors to the SDLC.

--business-models

Agentic Business Models

Defining the business models for Agentic AI. Does SaaS still work or FDE is the only way going forward? Explore & Share Business Models

The Ecosystem

From frameworks and infrastructure to models, tools, and platforms.

agentic-coding

Agentic Coding

$coding-agents
$ai-pair-programming
$code-review-for-agents
$spec-driven-development
$code-security-for-agents

active

frameworks

Agent & Tooling

$agent-frameworks
$orchestration-platforms
$sdks-and-developer-tooling
$multi-agent-systems

active

models

Models and Foundation

$frontier-model-providers
$developer-platforms
$applied-ai-tooling
$foundation-models

active

dev-tools

Agent Dev Tools & Frameworks

$development-frameworks
$apis-and-sdks
$testing-tools
$evaluation-frameworks
$mcp-tools

active

agentops

AgentOps & Traceability

$llm-trace-&-observability
$opentelemetry-for-agents
$model-serving-infrastructure
$inference-engines
$agent-sandboxes

active

enterprise

Enterprise & Security

$iam-for-agents
$tool-use-guardrails
$permission-frameworks
$banking-workflows
$compliance-automation

active

ecosystem-scan

Initializing agent...

Who This Conference Is For

This is a technical conference for people who ship agent systems. Expect architecture, debugging, evaluations, infra trade-offs, and production reliability conversations.

@builder

Agent Engineers & Builders

Hands-on engineers designing runtimes, tool chains, eval harnesses, and on-call operations for agents.

@ml-engineer

AI / ML Engineers

Shipping model integration, inference pipelines, eval workflows, and guardrails in production systems.

@platform

Developer Tool & Platform Builders

Building frameworks, SDKs, orchestration layers, observability, and deployment infrastructure for agent systems.

@product

Product Engineers & Technical PMs

Owning API-level product surfaces, eval targets, and agent behavior quality across releases.

@founder

Founders & Technical Leaders

Leading technical teams building agent-native products or internal automation platforms.

@researcher

Researchers & Applied Scientists

Driving applied research in multi-agent architectures, reliability, and evaluation methodology.

Technical Speakers. Demo-First Sessions.

We invite agent builders, researchers, operators, and practitioners building production-grade agentic systems. We also welcome technically savvy and passionate speakers who want to demo live, run real systems, and share debugging insights with the audience. This format is encouraged for speaker impact, not mandatory.

Suggested speaker format: 2-slide style + demos + live systems (optional)

Call for Speakers is open.

🧭

--two-slide-style--demo-first

Two-Slide + Demo-First

We encourage each talk to use two slides: opening context and closing takeaways. The rest can focus on the system itself.

Sessions can prioritize terminals, IDEs, logs, dashboards, traces, and live workflows over slide decks.