Every program ends with an agentic system you and your team keep running, not a slide deck and a certificate. Instructor‑led, built around the stack you already run.
Nine agentic AI courses that end with something running — an agent in production, a workflow redesigned and measured, a governance plan with an owner. Engineering, product, operations and leadership each get an entry point and an advanced path.
Certify Your TeamEngineers leave running agents they built themselves — from the first LLM integration, through hybrid retrieval and knowledge graphs, to a multi-agent system that operates without supervision.
Build production-grade AI systems in TypeScript — LLM integration, RAG pipelines, agents, and a capstone you deploy and keep.
Design systems that survive production — hybrid retrieval, knowledge graphs, multimodal pipelines, and agents that coordinate.
Both engineering tracks as one path — from TypeScript fundamentals through to autonomous systems, with two capstones.
21 hours building production multi-agent systems — anatomy, orchestration, guardrails, and a launch review.
One day building knowledge systems that hold up in production — five blocks, and three codebases you take home.
One day building agents that run on their own — a support agent, tiered memory, and a multi-agent research system you keep.
Product teams leave with the work itself redesigned — a defensible roadmap, AI features they can specify and measure, and a workflow proposal with numbers attached to it.
The full product path — discovery, prioritisation, roadmapping, and scaling a product organisation.
Bridge product and engineering on AI features — from the PRD through the metrics to the ethics.
21 hours redesigning how a team works — specs, documents, meetings, and a workflow proposal with its impact estimate.
One day that gives everyone one to three hours back, every day — no code, just the work rebuilt around AI.
Leadership leaves able to sign off — a strategy that survives a board question, and a governance plan for AI in the codebase with an owner on every control.
Strategy, workforce design, and the economics of an AI-native organisation — for the people who set direction.
21 hours governing AI across the development lifecycle — policy, oversight, licensing risk, and a rollout plan.
One day for the people who set direction — seven modules across four strategic phases, no code.
Engineering, product, operations and leadership, the people who set direction, on the same ladder from the first API call to the board discussion. Nobody else runs it as one path.
Every session is led by people who have built and run production AI systems, not by trainers working from someone else’s deck.
No passive learning. Every module ends with a deliverable your team keeps, and every program ends with something already running.
Programs are built on the systems and the policies you already have, so the work done in the room survives contact with your codebase.
Each participant earns a certificate issued through Accredible, verifiable by anyone and theirs to keep after they leave.
Part-time across the calendar or one intensive block, on site or live online, with only your own people in the room.
Module scores, capstone results and a readiness map per cohort, so the next budget line is an argument rather than a guess.
Training that ends with software doing the work, not with better prompts. Across the engineering track that means LLM integration and retrieval first, then orchestration, memory and guardrails, and finally a multi-agent system the team runs without supervision.
Generative work stops at output a person reviews. Agentic work adds planning, tool use, memory and guardrails so the system can act on its own and be held to a standard. The tracks here cover both, in that order.
Start with LLM integration and hybrid retrieval, move to orchestration and tiered memory, then build under review. The Agentic Engineering Certificate does it in 21 hours and closes with a production-readiness review.
Yes. Agentic Engineering is assessed on checkpoints and a final capstone, and issues a certificate of completion per participant. The Architecture Certificate covers multi-agent systems as part of a longer track.
Engineers already shipping LLM features start at Architecture or go straight to the 21-hour program. The leadership accountable for how AI enters the codebase takes Governance and SDL.
Yes. The Agentic Bootcamps are open to individual professionals. Each one is a single day on production systems, autonomous agents, productivity or executive leadership, held alongside the Disrupt AI Summit Series. The certificate programs run as private cohorts for company teams.
With a policy that names an owner for every control. AI Governance and SDL covers risk mapping across the development lifecycle, oversight and reporting, licensing and data risk, and leaves with a rollout plan and a maturity assessment.
The engineering track does. The Productivity and Governance programs require none, and the Executive Leadership Program is strategic throughout.
Both. Every program is instructor-led either way, and the assessments and the capstone run the same in each.
Certificate tracks run from three modules to sixteen, 15+ to 38+ hours. The 21-hour programs run seven hours a day over three consecutive days.
Each program lists its own prerequisite on its card. Four of the nine need nothing at all.
Organisations start with a conversation about where they stand. Professionals start with a bootcamp or a summit.