Design & Patterns
Planning, reflection, task decomposition, which pattern fits.
29 posts · showing 11–20
-
The Loop Decisions You Only Make Once
Most agent design choices are cheap to revise. Six aren't — and in every case the answer that ages well is the same one, for the same reason.
-
What Falling Inference Costs Change About Agent Design
Relaxed cost pressure mainly buys back the verification steps you declined. It doesn't rehabilitate filling the context or adding turns — those were quality problems wearing a cost disguise.
-
The Cost of Choosing Your Model Too Early
The choice is rarely the mistake — the accumulated compensations are. Prompts absorb quirks, the harness papers over weaknesses, and none of it looks like coupling until you try to change something.
-
Ambiguity Resolution Stays a Human Job for a While
An agent doesn't fail on ambiguity — it absorbs it, picks a reading, and produces a confident answer to a question nobody asked. Better models guess better; they don't guess less.
-
Why Agents Struggle Where There's No Feedback Signal
Coding agents work well because compilers exist, not because code is easy. Effectiveness tracks whether a domain has a fast, independent, specific verdict — and that's frequently something you can build.
-
Requirements Are the Bottleneck an SDLC Agent Can't Remove
Compress implementation to nothing and delivery barely moves, because implementation was never the long row in the table. The constraint is upstream, it's organizational, and no tooling touches it.
-
Agents Are Better at Writing Code Than at Deciding What to Build
Both feel like thinking about the problem, and only one has complete inputs and a checkable answer. The reframe that makes a model genuinely useful near a decision it shouldn't be making.
-
Half the Job Is a Real Answer: Designing for Partial Success
Thirty-one of forty invoices reconciled. Reporting success hides nine; reporting failure throws away thirty-one. The middle is where most runs land, and most designs can't express it.
-
Designing the First Turn: What Happens Before Any Tool Call
Everything after it inherits the frame it sets. Four things belong in turn one — and when a run fails at turn twelve, this is usually where the defect was introduced.
-
Progressive Disclosure: Give the Agent Tools As It Needs Them
The tool list is a per-call parameter, not a fixed property. Withhold the write tools until acting is authorized and a compromised context has nothing dangerous to reach for — enforcement, not instruction.