Agentic Futures Briefing
Executives setting AI direction, and engineers deciding what to learn next
Prerequisites: None for leaders. Engineers get more from it after module 19 or 20.
Last verified 2026-07-28
Learning objectives
- Name the six current-state shifts: spec-driven development, agent file taxonomies, context engineering, MCP adoption, computer/browser agents, multi-agent orchestration
- Assess the near-term signals: harness engineering as a role, interactive agent evals, agent identity and security, small language models
- Hold a view on the six-month horizon: agentic mesh, memory platforms, continual learning, world models, governance as architecture
- Translate each relevant signal into one concrete decision for your own organisation
- Know how to keep the map current after the session
What's in this module
6 lessons · 7 exercises · ~6 min reading
Starts withWhy horizons beat headlines~1 minExecutive summary
You will learn where agentic engineering is heading across three horizons: what's standard practice now, what arrives within a quarter, and what's forming six months out. End state is a shared map of the signals that matter, separated from the noise, with a view on what each means for your organisation. After this module you can prioritize what your teams learn next, decide which signals justify investment now versus watching, and brief your own board with confidence.
Sources
All signal sources live in futures-radar.yaml with the radar itself, reviewed monthly.
Prefer the live room?
This module also runs inside our in-person bootcamps and workshops in Copenhagen.
Rolling this out across an organisation?
We run this material as executive briefings and team programmes, tailored to your stack, your data policies, and your pace.
More in Track F
Prompt Engineering Deep Dive
The complete prompting toolkit, from structure and roles to hallucination control and complex industry prompts, plus how to measure prompt quality with evaluations.
Claude Code for Developers
How to run Claude Code as a professional engineering tool: operating manuals, subagents, hooks, skills, MCP, and git/CI workflows.
Agent Harness Engineering
How agents actually work under the hood: the model supplies intelligence, and everything else is a harness you can build.