Guides for forward deployed work.

Turn customer requirements into PRDs, specifications, BDD examples, agent-built code and verified releases. Covers skills, MCP, code property graphs, evals, AgentGym and controlled improvement, with a tested Python/SQLite companion.

Build the layer that turns a model into a system a customer can run: the loop, instructions, context and caching, tools and MCP, skills, verification, permissions, credentials, sandboxes, cost, the customer eval and self-improving harnesses, with the 2026 evidence beside each decision and a tested Python companion.

Connect tools, agents, interfaces and commerce through MCP, A2A, UCP, ACP, AP2, x402 and MPP. Learn delegated authority, recover uncertain effects and run a tested Python companion with a real local MCP track.

Build the data layer behind AI agents: transactional state, vector retrieval, knowledge and context graphs, ontologies, feature stores, catalogs, Open Knowledge Format, MCP and recoverable actions. Includes tested Python and PostgreSQL exercises.

Design agents that act for one person inside an organization: delegated identity, a deterministic gatekeeper, exact-action approvals, memory and recall, voice and messaging surfaces, decision models, and a tested reference build on Google ADK.

Understand vectors, probability, evaluation, gradients, capacity and data visualisation through small worked examples. Includes exercise solutions and runnable calculators.

Establish the mandate, hire and develop the team, govern customer engagements and reconcile the economics. Four worked cases and 24 editable operating forms.

Design, ship, and operate AI systems in customer environments. Four worked engagements, from permission-aware retrieval to an offline deployment, with nine executable lab tracks.

Ten customer scenarios with architectures, capacity calculations, failure paths and an executable verification companion.

Eight worked decompositions, six customer conversations and a learning round, each with a transcript that passes, one that loses, and the card that scores them.

Ten graded take-home projects with worked, executed solutions, a scoring rubric and the walkthrough that decides the round.

Make the move into forward deployed work. Learn to scope the customer problem, build the proof and own the deployment.

Understand the market behind the role: enterprise deployment, the technical stack, engagement economics and hiring.