What's actually in an AI consultant's tool bag, 2026

Every "best AI tools" listicle is affiliate bait. This one isn't — no affiliate links, and where a tool is ours we say so with a grin. It's what we and the practitioners around us actually use. The Stack Survey will correct us in public as the data comes in.

What our own traffic says

The receipts, not the vibes

Which agent families actually touch this site, live from the Bot Ledger. Caveats, because they matter: our traffic is a floor not a census, our audience self-selects, and a user-agent is a claim not an ID.

—

of our crawl traffic is workbench (agents on an errand), 30 days

—

the most active AI crawler family on us this month

—

the AI tool sending us the most humans (referrals)

1. The agentic workbench

The consultant's primary surface in 2026, not a developer nicety. Deliverables — the scoping doc, the migration, the eval harness — increasingly get built in these, not typed into a blank page.

Claude CodeTerminal-native agentic coding. Where a lot of our own delivery work happens. Bites when you let it run unsupervised on a big change — review the diff, always.

CursorThe IDE-shaped entry point most teams meet first. Good for consultants embedding with an existing dev team on their editor.

Codex-class CLIsThe category, not one product. Pick the one your client's stack and security team will actually approve; that constraint matters more than the benchmark.

2. The connected workspace

Agent workspaces that reach your tools, plus the MCP servers worth installing so your agent can query real data mid-engagement.

Cowork-class workspacesAgent workspaces that connect to your docs, mail and calendar. Useful for the non-code half of consulting; watch what you connect and what it can do.

The Project Wrecked MCP server OursYes, ours — disclosed with a grin. Read-only tools for model deprecations, rates, a red-flags checklist and our crawler stats, installable in any MCP client. /mcp.

Provider + vendor MCP serversInstall the ones that expose data you check often (issue trackers, docs, cloud consoles). Every install is an attack-surface and a dependency — curate, don't hoard.

3. Delivery & evidence

The boring spine that separates a consultant from a demo. Unglamorous, and the first thing that saves you in a dispute.

Versioned docs & decision logsPlain, diffable, dated. The record of what was decided and why is worth more than any deck when a stakeholder's memory conveniently changes.

An eval harnessA few hundred representative inputs and approved outputs, built from day one. It's the difference between validating a model swap in days and arguing about vibes for a month.

A data audit, before you scopeNot a tool, a habit. The bodies are always in the data — go find them before you sign.

4. The commercial layer

Proposals, contracts, and pricing — the part that turns capability into an invoice. Where our own store products genuinely belong (disclosed as ours).

Proposal & SOW toolingWhatever you write contracts in, with a real model-deprecation clause in the template. The SOW Toolkit and AI Pricing Framework Ours are what we reach for.

A vendor-evaluation rubricWeight deprecation behaviour alongside capability and price. The Vendor Evaluation Matrix Ours has the column; the Platform Ledger has each provider's habits, live.

5. The watchlist

Explicitly provisional — what we're evaluating, not endorsing. Here so you can watch us change our minds in public.

wreck-watch OursOur own free CI check that warns when your pinned model IDs are on the departure board. Shipping shortly — watch this space.

Agent-eval & observability toolingThe category is moving fast and we don't have a confident pick yet. When we do, it'll show up here — and the survey will tell us if we're wrong.

🗳️

This is our opinion, grounded in our own logs. The honest version is a dataset: the Stack Survey is coming, and once enough practitioners answer, its aggregates will take over this page and correct us where we're wrong. No affiliate links here, ever — if that changes, we'll disclose it per link, in this same voice.