$ agent-estimate --compare

Three ways
to know.

No estimation, manual, or agent-estimate — three approaches to scoping AI-agent work. Here's how they actually compare, on the dimensions that matter.

· 250+ dispatches validated (May 2026) · 8 dimensions · no marketing

agent-estimate --compare --tldr zsh

$ agent-estimate --compare --tldr
 
scoring against: speed, accuracy, AI-fit, ci, ux
────────────────────────────────────────────────
 
  ✗ --no-estimate    0/5  risky for anything with a deadline
  ~ --manual         2/5  slow, optimistic, AI-blind
  ✓ --agent-estimate 5/5  calibrated, fast, CI-ready
 
recommendation ─────────────────────────────────
  use agent-estimate when AI agents touch your sprint.
  use manual for judgment-heavy planning.
  use no estimate for throwaway code only.
 
  → see full breakdown below ↓

OVERVIEW

At a glance.

--no-estimate RISKY

No estimation

// Ship and hope.

Zero upfront cost, but scope creep, missed deadlines, and surprise failures. Fine for prototypes and throwaway experiments. Dangerous for anything with a deadline.

--manual SLOW

Manual estimation

// Human guesses in planning meetings.

Slow (30–60 min per sprint), systematically optimistic, and blind to AI-specific speed differences. The estimates degrade as model capabilities change quarter to quarter.

--agent-estimate RECOMMENDED

agent-estimate

// PERT math + METR data + dependency analysis.

Calibrated three-point estimates in ~2 seconds. Accounts for model-specific reliability limits, review overhead, and multi-agent parallelization. Improves via ae calibrate.

DIFF

Side-by-side, dimension by dimension.

$ agent-estimate --compare --table

agent-estimate compare · table diff

dimension --no-est --manual --agent-estimate

Time to estimate -0 ~30–60 min/sprint +~2 seconds

Accuracy -N/A ~±50–100% +85% within ±30%

AI speed awareness -no ~rarely +per-model multipliers

Dependency analysis -no ~whiteboard +automated wave planning

METR reliability -no ~no +built-in thresholds

CI integration -no ~no +GitHub Action

Review overhead -ignored ~sometimes +3 modes (std/complex/3-round)

Improves over time -no ~slowly +ae calibrate

8 dimensions · 3 approaches +8 ~0 -0 winner: agent-estimate

DECIDE

When to use each.

decide.sh bash

# pick by project context
case $context in
 
  prototype)
    estimator="--no-estimate"
    # throwaway, near-zero cost of being wrong
    ;;
 
  mature_team)
    estimator="--manual"
    # judgment-heavy, distrusts automation
    ;;
 
  ai_workflow)
    estimator="--agent-estimate"
    # AI agents, CI budgets, repeatable
    ;;
 
esac

prototype → --no-estimate

Prototyping, hackathons, throwaway scripts where the cost of being wrong is near zero.

mature_team → --manual

Established velocity, judgment-heavy work (design, strategy), or stakeholders who distrust automation.

ai_workflow → --agent-estimate

Sprint planning with AI agents, CI pipelines with time budgets, multi-agent workflows, repeatable estimates across changing models.

FAQ

Frequently asked questions.

?How accurate is agent-estimate?

› Across 250+ validated dispatches (May 2026 corpus), 61% of estimates land within ±30% of actual duration out of the box. With calibration modifiers (spec clarity, warm context, agent fit), accuracy improves to 85% within ±30%. ae calibrate feeds actual results back in.

?Does it work with models other than Claude?

› Yes. Built-in METR thresholds cover Claude (Opus, Sonnet, Haiku), GPT-5.5/5.4, and Gemini 3.1 Pro. Custom thresholds for any model in your agent config YAML.

?How does PERT estimation work?

› PERT uses three time estimates per task — optimistic, most likely, pessimistic — to compute a weighted expected duration: (O + 4M + P) / 6. Produces a probability distribution rather than a single-point guess.

?Can I use it without the CLI?

› Yes. The Claude Code plugin adds /estimate as a slash command. The GitHub Action runs estimates in CI and posts results as PR comments. Same structured output across all three.

$ start estimating

Stop guessing. Start shipping.

One command. No account. Reports in seconds.

$ pip install agent-estimate ← back to landing

Three waysto know.