Structuring

Clarify structure and intent. 4 optimizations.

i.

Add worked examples to the prompt (few-shot), or curated example queries for data agents

Put a few solved examples of the task in the prompt (the input and the exact output wanted), or give a data agent commented example queries for its custom metrics and an index of past queries it retrieves per question.

Mixed qualityHigher costSlower

Tier 3 · tuning · changes prompt · any agent · 7 sources, 6 measured
ii.

Avoid few-shot ruts

An agent's own history, and any examples in its prompt, act as few-shot demonstrations: when the context fills with near-identical action-observation pairs (twenty similar items in a row, a retried call), the model tends to copy their surface form instead of judging the current item.

Mixed qualityMixed cost

Tier 3 · tuning · changes prompt · any agent · 13 sources, 8 measured
iii.

Dynamic context injection

Put the runtime facts the model cannot know into its context each run: today's date and timezone, the working directory, OS and git state, the tools available, the user and locale.

Better for brandMixed quality

Tier 3 · tuning · changes prompt, context · any agent · 9 sources, 4 measured
iv.

Restructure the system prompt: every requirement once, up front, in named sections; nothing the model doesn't need

Rewrite the system prompt so that each requirement the task has (constraints, the answer format, the completion check, how to work efficiently, the domain procedure) is stated once, up front, in a named section, and remove instructions the model does not need.

Lower costFasterMixed quality

Tier 3 · tuning · changes prompt · any agent · 11 sources, 2 measured

Try it for yourself

Paste this into Claude Code, or any coding agent, in your agent's repo to check it for these optimizations.

Read these agent optimizations (Prompts: Structuring), each with the signs that it applies:
- 3.a.i Add worked examples to the prompt (few-shot), or curated example queries for data agents: https://mahalsystems.ai/aot/optimizations/few-shot-examples.md
- 3.a.ii Avoid few-shot ruts: https://mahalsystems.ai/aot/optimizations/vary-few-shot-examples.md
- 3.a.iii Dynamic context injection: https://mahalsystems.ai/aot/optimizations/inject-runtime-context.md
- 3.a.iv Restructure the system prompt: every requirement once, up front, in named sections; nothing the model doesn't need: https://mahalsystems.ai/aot/optimizations/restructure-system-prompt.md
- 9.b.i Make the final answer reliably extractable: state the format, extract robustly, force an answer at the limit: https://mahalsystems.ai/aot/optimizations/extractable-final-answer.md
Then check whether any of them applies to the agent in this repository. Look for each one's signs under "When it applies" in its code, prompts and tools, and in any traces or eval results you can find. Tell me which apply, strongest first, with what you found for each. Don't change anything yet.

Structuring

Add worked examples to the prompt (few-shot), or curated example queries for data agents

Avoid few-shot ruts

Dynamic context injection

Restructure the system prompt: every requirement once, up front, in named sections; nothing the model doesn't need

See also

Make the final answer reliably extractable: state the format, extract robustly, force an answer at the limit

Build better agents, weekly

You're on the list.