New to this library, not necessarily new to the world.
Thariq Shihipar presents a field guide to working with Fable: expose a model's uneven capabilities through the right tools, identify unknowns before long agent runs, use blind-spot passes, prototypes, interviews, references, and implementation notes, and judge the work by the value it creates rather than the code it generates.
AI Engineer · Source dated 6 Jul 2026
A question-driven editorial route through selected talks in the rolling Coding Agents playlist published by the AI Engineer channel—not complete event coverage. The speakers remain the sources for their individual claims.
AI Engineer · Source dated 31 Jul 2026
From David Ondrej Podcast — selected agentic engineering conversations
David Ondrej · Source dated 27 Jul 2026
An Italian-language playlist about coding-agent supervision, specifications, behavioral testing, model evaluation, developer attention, local inference, and how automation shifts value from implementation effort toward design and invention. The guided summary offers a short route through the most useful starting points.
Salvatore Sanfilippo · Source dated 10 Aug 2026
Robert C. Martin and Kent C. Dodds discuss why software architecture remains durable as agents take over more implementation, how structural metrics and tests can close the agent feedback loop, why design judgment still depends on experience, and why engineers need direct empathy for the people using their products.
Kent C. Dodds (plus) · Source dated 22 Jul 2026
From Raising an Agent Season 2 - Series
Amp, Inc. · Source dated 17 Jul 2026
Armin Ronacher and Ben Vinegar track agentic coding through monthly conversations about models, harnesses, software quality, open source, infrastructure, economics, and the changing role of developers. Episode 11 brings in Geoff Huntley to discuss durable agent execution, modifying running software through an LLM, the difficulty of inspecting ad hoc tool code, and experiments made affordable by subscription pricing.
Armin Ronacher
Source dated 15 Dec 2025
Source dated 22 Jan 2026
Source dated 16 Feb 2026
Source dated 12 Mar 2026
Source dated 10 Apr 2026
Source dated 11 May 2026
Source dated 12 Jun 2026
Source dated 13 Jul 2026
A 2026 map of coding-agent work: brief the task, preserve context, verify behavior, keep consequential decisions human, and scale only what works.
With Agents · Post published 28 Jun 2026
How to brief, place, delegate, and verify a coding task with Amp.
With Agents · Post published 28 Jun 2026
How to decide which coding-agent context belongs in chat, AGENTS.md, skills, work items, docs, tests, and saved results.
With Agents · Post published 2 Jul 2026
A practical acceptance framework for agent-written code: the harder a failure is to undo, the stronger the evidence required.
With Agents · Post published 28 Jun 2026
How to keep connected agent work in one thread, split only when separation helps, and carry accepted state across the boundary.
With Agents · Post published 28 Jun 2026
Mario Zechner explains why he built Pi as a minimal, self-modifying coding-agent harness after frustrations with opaque context management and feature-heavy tooling. The talk covers Pi's small core and extension model, Terminal-Bench results, agent spam pressure on open-source maintainers, and a practical warning to slow down, scope agent tasks, and keep humans responsible for critical code.
AI Engineer · Source dated 16 Apr 2026