Tools · AI Estimates
Time, tokens, dollars, and how many people you still need. AIdaScore prices the work you did — this prices the work you haven’t.
Free. Runs in this tab — nothing about your project leaves the browser.
P80 39.2 days · bound by your review — 93% of the work is you, not the agents
Confidence: priors · band ±53%. 19 coefficients are assumed, not measured.
Cost and headcount move by different amounts. Averaging them into one flattering multiple is how estimates start lying, so they are never averaged.
Elapsed is the larger of agent time and review time, never the sum — which is why past a point a faster model changes nothing, and eight agents are not eight times faster.
Requirements are classified and consumed commodity-first. The expensive tail is exactly what you buy chasing the last slice of parity.
Share of a from-scratch build each class costs. A novel requirement is roughly twenty times a shelf one — so a CRM that is 40% off-the-shelf and a core banking platform that is 5% produce genuinely different answers, without anyone drawing a curve by hand.
A 220-person-day product gets a transformation. A 120,000-person-day programme gets a rounding error — and, at these settings, a penalty.
| Shape | Size | Off the shelf | People | Build leverage |
|---|---|---|---|---|
| Simple SaaS product | 220 PD | 44% | 1 | 3.0× |
| Enterprise CRM rollout | 3,200 PD | 40% | 12 | 7.7× |
| ERP finance + supply chain | 30,000 PD | 18% | 115 | 2.1× |
| Core banking migration | 120,000 PD | 5% | 525 | 0.8× |
Core banking comes back at 0.8× — below one. With 5% of the surface available to adopt and one reviewer absorbing the output, the model says agents cost you more than they save. A tool that could not return that answer would not be worth running on the other three.
The same brief, every model. Enterprise CRM, at defaults.
| Model | Elapsed | All-in | Tokens |
|---|---|---|---|
| Claude Opus 5 | 25.6 days | $12.7k | 432.7M |
| Codex GPT-5.x-codex~ | 27.1 days | $12.7k | 458.2M |
| Claude Sonnet 5 | 27.9 days | $13.4k | 472.1M |
| DeepSeek V3.x~ | 33.6 days | $15.5k | 577.0M |
| Qwen3-Coder~ | 35.3 days | $16.3k | 610.9M |
| Claude Haiku 4.5 | 37.9 days | $17.7k | 662.9M |
Fastest to slowest is 25.6 to 37.9 days — a 1.5× spread on a decision people argue about as though it were 10×. ~ marks a row whose pricing or first-try rate is assumed rather than published.
A confident wrong number is the failure mode. So every coefficient carries its provenance, and the tool prints the table on demand.
Only the Anthropic pricing is published. Every load-bearing number — first-try rate above all — is a prior, not a measurement.
More evidence narrows P50 to P80. Nothing collapses it to a point, because nothing honestly can.
“9.5×” without its scope is the most misleading thing this could print. Build and programme are always returned together.
Treat every number as a shape, not a quote.
Pick the nearest shape, correct the parameters that make yours hard, and read the band. Sign in and it opens in this tab.