Free tools

Tools for people building agents, not buying hype

Five tools covering the decisions an agent project actually turns on — whether to build, what to specify, why it won't run unattended, and whether the vendor in front of you has done this before. No email gate on any of them.

Get my free blueprint

free AI agent planning tools

Five free AI agent planning tools are published here: a readiness checklist that screens a workflow before any build, a calculator that sizes the hours one workflow consumes, a spec generator covering memory, context budget and guardrails, a 12-criterion vendor scorecard, and a 15-question production diagnostic. Each runs in the browser and shows its result with no email required.

Nothing is stored or transmitted — every calculation happens in the page. What none of them can do is replace scoping: they narrow a decision and tell you which question to answer next.

Every one of these exists because we needed it ourselves or got asked the same question enough times to write it down. None of them gate the result behind an email — you get the answer, and if you want a human to look at it, that is your choice rather than the price of entry.

They are ordered below by where you are in the project, because using the production diagnostic before you have built anything is as useless as using the readiness checklist after you have already shipped.

What these tools can and cannot tell you

Each one narrows a single decision from inputs you already have: how long a task takes, how a vendor answered a question, what an agent is allowed to spend. None of them can see your systems, so none of them can promise a delivery date or an outcome. If the open question is whether an agent is the right shape of solution at all,the difference between an AI agent and a chatbot settles it faster than any calculator, andno-code agent platforms compared covers the cases where a build is not needed.

Two questions follow every result. How long the build takes is answered inthe production timeline breakdown, and who should do it is answered bythe questions to ask an AI agent developer before hiring — the same questions the vendor scorecard is built from.

Choosing a vendor

Vendor scorecard

Is this AI agent development company worth hiring?

12 criteria across evidence, architecture, control and commercial terms. Four are deal-breakers that no total can rescue. Score your whole shortlist — including us.

Open tool

Before you build

Readiness checklist

Is this workflow worth automating at all?

Eight yes/no questions on scope, data access, volume and ownership. Tells you what to fix before an agent is even the right conversation.

Open tool

ROI calculator

What is this repetitive task actually costing us?

Put your own numbers on one workflow and see the year laid out. Uses your figures rather than a heroic number picked to sound good.

Open tool

Designing the build

Spec generator

What decisions do I need to make before writing code?

Six questions in, a starter spec out: memory schema, context budget, typed tool contracts, fallback cascade and guardrails. Copyable YAML.

Open tool

After you build

Production readiness diagnostic

Why can I not leave this agent running unattended?

15 questions across the five failure classes that actually break agents. Scores each class and hands back an ordered fix list.

Open tool

Why these are free and ungated

An email gate on a calculator buys you a list of people who wanted a number and now resent you slightly. We would rather the tool be good enough that some of the people who use it choose to get in touch — and that the ones who do arrive already knowing what they need.

Each tool does offer to send its result to us, with the full working attached, if you want a second opinion. That is a button, not a wall.

Questions

Which tool should I start with?

It depends where you are. Comparing vendors: the vendor scorecard. Deciding whether a workflow is worth automating: the readiness checklist, then the ROI calculator to size it. About to build: the spec generator. Already built something that will not run unattended: the production readiness diagnostic.

Do I have to give you my email to see the results?

No. Every tool computes its result in your browser and shows it immediately. Each one then offers to send the result to us with the full working attached if you want a second opinion, but that is optional and the answer is already on screen.

What is the difference between the readiness checklist and the production readiness diagnostic?

The checklist is a pre-build question: is this workflow repetitive, well-scoped and high-volume enough to justify an agent. The diagnostic assumes you already have a working agent and asks which of the five failure classes is stopping it from running unattended. Different stage, different questions.

Can I use the vendor scorecard on you?

That is the point of publishing it. Our answers to the four deal-breaker criteria are in our case studies: a documented failure taxonomy with frequencies, agents running unattended with restart counts, spend ceilings enforced in code, and self-hosted deployment by default.

Get your agent blueprint — free.

Tell us what eats your week. We’ll come back with a concrete plan for the first agent to build and what it’ll automate — before you spend anything.

Goes straight to hello@iamagentman.com — we read every message ourselves. Prefer to answer three questions instead?Build your blueprint.

Explore more

AI agent development→Case studies→AI agent framework comparison→Hire an AI agent developer→How to hire an AI agent developer→AI agent development cost→Free agent blueprint→