Deep technical talks for CTOs, agent builders, AI researchers, and technical leaders shipping production-grade agent systems.
Attending instead? for launch updates.
// our definition
Agent Engineering is the discipline of designing, building, evaluating, and operating AI agents reliably in production. It focuses on the engineering aspects of the Agent Development Lifecycle, including prompt, context, harness, inference, memory, evaluation, and code engineering practices.
AgentEng (Agent Engineering Conference) is the first conference dedicated to the engineering practices behind production-grade AI agents of every kind, from coding agents and research agents to customer-facing agents, domain-specific agents, and autonomous multi-agent systems.
As agents become core to how software and businesses are built, the engineer's role shifts from writing code to directing, reviewing, and orchestrating the agents that do the work.
Agents have their own development cycle, the Agent Development Lifecycle (ADLC), covering build, test, deploy, and monitor with iteration and governance running throughout. The conference covers every aspect of the ADLC and the tools, frameworks, and infrastructure that support it.
We bring together practitioners doing this in production, working with real constraints, real trade-offs, and real systems.
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::08
Inference Engineering
discipline::09
Agentic Engineering
discipline::∞
Context, evals, memory, harnesses, skills, guardrails, inference, and agentic orchestration converge in production systems engineering.
Prompt Engineering
Context Engineering
Harness Engineering
Eval Engineering
Memory Engineering
Skills Engineering
Guardrail Engineering
Inference Engineering
Agentic Engineering
discipline::∞
... *.Engineering
Agent Engineering
Production agentic systems require more than prompt engineering. They depend on context, harnesses, evals, memory, skills, guardrails, inference, and agentic orchestration working together as one engineering discipline.
We are looking for AI engineers, AI researchers, CTOs, and CEOs who ship agents in production and know the engineering practices that make them reliable. We want highly technical talks with live demos, real architecture, and lessons from running agentic systems at scale.
We would love to hear about your engineering journey.
These are the engineering themes we are programming. If your system or your company operates in one of these areas, please get in touch.
Building, compressing, and routing the right context to the model.
fit: Companies working on context optimisation and context windowing.
The infra around the model: tool runtimes, sandboxes, agent loops.
fit: Companies innovating on agent harnesses and coding harnesses.
Long-term, short-term, episodic, and semantic memory in agents, including tool search and retrieval over that memory.
fit: Agent-memory and memory-architecture companies, vector databases, and retrieval platforms.
Designing, packaging, and composing reusable agent skills and tools.
fit: Companies building skill libraries, skill registries, and tool-composition platforms.
Serving, scaling, and optimising model inference for agentic workloads.
fit: Inference platforms, model-serving companies, and teams optimising agent latency and cost.
Multi-agent coordination, planning, and control flow at scale.
fit: Companies building agent runtimes and orchestration layers.
Measuring agent behaviour: regressions, traces, replay, scoring.
fit: Companies building agent observability and evaluation platforms.
Safety, policy, refusal, and tool-use boundaries in production.
fit: Companies focused on guardrails and runtime agent safety.
Automating the entire software development lifecycle and engineering with AI agents.
fit: Teams and companies automating software engineering itself with AI agents.
Tell us which theme fits, your talk idea, links to prior work, and the system you would talk about. We respond to every serious application, usually within 48 hours.
Reach a curated room of CTOs, agent builders, and technical leaders shipping production agentic systems.
The founders edition is a one-day single-track conference, so partnership slots are intentionally limited.
Founders-edition partnerships are filling fast.
Founding Sponsor
Lead partner of the founders edition.
Gold Sponsor
Booth and a speaking slot.
Silver Sponsor
Website visibility and digital presence during the conference.
Founding, Gold, and Silver packages are open for technically relevant partners.
~5,000
London Agentic AI Builders
Technical
Speaker Style
Practical
Systems + Lessons
Partner with a smaller, highly technical room of curated builders.
$ Courthouse Shoreditch, London · 16 July 2026 · max 200 attendees
Join a curated room of technical builders at Courthouse Shoreditch, London for a single-track day on engineering agentic AI systems.
Day
Attendees Max
Single Track
Courthouse Shoreditch → London → 16 July 2026
We invite agent builders, researchers, operators, and practitioners working on production-grade agentic systems. We are looking for technically grounded talks on how agents are designed, evaluated, deployed, and operated. Demos and live walkthroughs are welcome when useful, but the core requirement is engineering depth.
We are looking for clear engineering talks on agent systems: architecture, orchestration, evals, memory, tools, context, and production tradeoffs.
Demos, traces, logs, or workflows are welcome when they make the technical point sharper.
Talks can walk through real systems, architectures, evaluation pipelines, operational lessons, or design decisions from building agents.
Where you can, reference real system behaviour: latency, reliability, cost, evaluation results. The more grounded in reality, the better.
Speakers are invited for production stories, technical arguments, and engineering lessons from real agent systems.
This is a technical conference for people who ship agent systems. Expect architecture, debugging, evaluations, infra trade-offs, and production reliability conversations.
Hands-on engineers designing runtimes, tool chains, eval harnesses, and on-call operations for agents.
Shipping model integration, inference pipelines, eval workflows, and guardrails in production systems.
Building frameworks, SDKs, orchestration layers, observability, and deployment infrastructure for agent systems.
Owning API-level product surfaces, eval targets, and agent behavior quality across releases.
Leading technical teams building agent-native products or internal automation platforms.
Driving applied research in multi-agent architectures, reliability, and evaluation methodology.
No marketing fluff. Real constraints, real trade-offs, real systems.
Talks focus on agent systems, tradeoffs, implementation detail, and lessons from real engineering work.
Agent systems are non-deterministic. We value honest discussion of failures, constraints, and operational surprises.
Speakers are invited for practical engineering depth, clear relevance, and real experience building agent systems.
A manifesto, a mindset, and a set of engineering themes for practitioners building serious agentic systems.
// organisers
Built on community, shaped with practitioners, speakers, and collaborators.
Superagentic AI
Advancing the Agent Engineering discipline and practice
Conference Chair & Curator · Ex-Apple Engineer (6 years) · Organizer, London Agentic AI
Everything you need to know about the Agent Engineering Conference
One day. Single track. The opening keynote and closing panel both span all agent engineering disciplines, with a dedicated technical talk in between for each engineering theme. The agenda below is tentative and subject to confirmed speakers.
Tentative. Themes and timings will be confirmed as the lineup is set.
Suggest a technical speaker, enquire about sponsorship, or get in touch with the team.
Invited speakers · sponsorships open · tickets waitlist
$ Quick response guaranteed