AI Development208 articles · Page 12 of 18

AI Development

Implementation notes for building AI tools around real business data, handoffs, review queues, and safeguards.

An illustrative six-clip timeline shows a human save creating revision 26 while an agent full write based on revision 25 stops at a stale-state conflict; reversal and export remain separate decisions.

AI Development·July 13, 2026

When the editor and the agent grab the same cut

FableCut exposes one shared video timeline to humans and agents. Its most revealing behavior appears when both try to change the same cut.

8 min read

Constructed diagram

AI Development·July 8, 2026

The AI coding tool is now an endpoint setting

Ask a Mac admin which AWS account a developer's Claude Code install is actually authenticating against, and most can't answer without opening a terminal and guessing.

7 min read

Constructed diagram

AI Development·July 7, 2026

When a coding agent misfires, the first 48 hours matter

GitHub Copilot session streaming gives enterprises a new kind of evidence: prompts, responses, and tool calls. The urgent question is who pulls the 48-hour record before it disappears.

8 min read

A gateway control sheet records identity, policy, telemetry, and spend caps before developer Claude Code access expands.

AI Development·July 5, 2026

Before Claude Code spreads, put the gateway in writing

One developer can wire Claude Code to Vertex AI in an afternoon. The tenth developer turns that same setup into questions about identity, spend, and who gets removed on their last day.

7 min read

A model facts register showing model rows with freshness dates, source links, capability boundaries, latency and cost notes, approval owners, and recheck triggers.

AI Development·July 3, 2026

The model decision is stale before the meeting ends

AWS just admitted, in its own release notes, that the facts a model-picking meeting needs are scattered across console pages, documentation, and regional API calls. Its fix is a catalog. Yours still needs an owner.

8 min read

A failure population ledger with many logged AI workflow failures grouped into recurrence clusters by category, tool path, environment, reviewer label, and proof of disappearance.

AI Development·July 1, 2026

One bug or two? What OpenAI's 18-year-old crash teaches AI teams about counting failures

OpenAI spent years chasing a crash that looked like one bug and turned out to be two, a bad server and an 18-year-old race condition, both wearing the same symptom. The breakthrough wasn't a clever fix. It was refusing to explain any single crash until they'd counted every crash. AI workflows fail the same way, and most teams still debug them one weird case at a time.

8 min read

An agent effort budget card for a Claude Sonnet 5 migration showing effort level, tool limit, latency target, review gate, fallback model, tokenizer adjustment, and stop rule fields.

AI Development·July 1, 2026

Claude Sonnet 5 didn't just get cheaper. Your agents now need an effort policy.

The upgrade note said Sonnet 5 was the most agentic version yet, and everyone read it as a price cut. The operator question buried in the release is different: how hard should this workflow be allowed to try?

8 min read

Reviewer comparing a vague AI output with a structured handoff packet before approving workflow work.

AI Development·June 29, 2026

The handoff note your AI workflow should leave before approval

Before a reviewer approves AI work, the queue should leave a compact handoff note: source, proposed action, missing fields, risk flags, owner, and rollback hint.

8 min read

Duplicated file blocks shrinking through a small local proxy into compact glowing tokens, with a steady glass quality arc on a midnight navy background with cyan and violet light.

AI Development·June 28, 2026

Your coding agent needs a calorie label for context

A coding agent can look productive while paying, over and over, to send the same files back through the model. Before you optimize that, you have to be able to read it.

9 min read

Cool-toned software review bench with blank evidence cards, approval controls, and abstract deployment server blocks.

AI Development·June 25, 2026

The two-hour AI pull request needs a harness, not a hero reviewer

AI coding agents can generate a convincing pull request in two hours. The operator problem is review legibility: the missing receipt that makes approval safe.

7 min read

Abstract courier path where a request token enters a glowing local vault and only a result returns, the raw key never leaving the core.

AI Development·June 21, 2026

Give the agent a ticket, not the key

When an AI agent needs Stripe access, the default move hands it the raw key. A better pattern gives it a secret handle, a host allowlist, and a daemon that owns the call. Here is the courier policy that makes that concrete.

9 min read

Cool-toned studio scene of blank layered footer tags trailing a single commit strip, with no readable text.

AI Development·June 20, 2026

The AI contribution label belongs in the commit, not the meeting notes

You run git log and the last line of the commit reads Co-authored-by: Claude. It shows up in the contributors list like a teammate who just joined. It isn't one. That gap is the whole post.

7 min read