AI Tools tool

Agent tool permission matrix

Decide which tools an agent can read, write, approve, or execute without creating avoidable risk.

Fast answerA permission matrix for read, draft, execute, approve, and rollback authority.

Inputs

What to collect

Tool list	Repo, shell, browser, database, CRM, ticketing, docs, email, deploy, or billing systems.
Action type	Read, create draft, modify, delete, execute, approve, or spend money.
Recovery path	Logs, diff review, backups, rollback, and owner notification.

Method

How to use it

1	Default new tools to read-only until a recovery path exists.
2	Require approval for destructive, external, or customer-visible actions.
3	Log enough context to reconstruct every agent action.

Output

How to read the result

Read-only	Broad context	Useful for research, triage, and draft plans.
Write draft	Review required	Good for code changes, docs, tickets, and responses.
Execute	Narrow and logged	Reserve for repeatable low-risk workflows with rollback.

Thresholds

Useful vs risky

Healthy	Every write action has a named owner and reversible path.
Risky	The agent can execute tools that humans cannot easily audit.

Buyer tools

Quick checks before a shortlist

All 20 tools

AI Modelsai model cost calculator

AI model cost calculator

Use this before choosing a default model. The useful answer is not the cheapest token price; it is the cheapest solved task with acceptable latency and failure rate.

AI Modelsllm context window planner

LLM context window planner

Long context helps only when the model still follows instructions near the end of the prompt. This planner forces a fit check before a bigger context tier becomes the easy answer.

AI Modelsprompt routing savings estimator

Prompt routing savings estimator

Routing is useful when easy prompts are common and failure is observable. It is wasteful when every task is rare, expert, or hard to classify.

AI Modelsinference latency budget planner

Inference latency budget planner

A fast model can still feel slow if retrieval, tool calls, retries, and post-processing are not budgeted. This planner keeps the whole user path visible.

AI Modelsmodel eval sample size planner

Model eval sample size planner

Small evals can still be useful if they are realistic and repeated. This tool makes the sample deliberate: enough cases to catch regression, not so many that no one maintains it.

AI Toolsrag chunk size planner

RAG chunk size planner

Chunking is not a magic number. The right size depends on the shape of the source and whether the model needs local detail, full sections, or cross-document synthesis.

AI Toolsembedding storage cost estimator

Embedding storage cost estimator

Embedding cost is rarely just the first import. Refresh cycles, duplicate content, metadata, backups, and permission filters decide whether the system stays manageable.

AI Toolsapi rate limit planner

API rate limit planner

Rate limits are product constraints. This planner helps choose batching, backoff, queueing, and multi-model fallback before launch traffic teaches the lesson.