Give Them the Harness

By Craig M. Brown · 2026-06-03 · Future of work, AI-native talent, agent harness

A six-week story worth stopping for

In November 2025, Andrej Karpathy wrote about 80% of his code by hand. By December, his agents wrote 80% of it. He called it the biggest change to his workflow in two decades — and it took roughly six weeks. The thing that changed wasn't the model; the model barely moved. What changed was the harness around it. It's the same lesson we keep landing on at BlindOracle, and the one we argued from the cost side in our benchmark on model spend: the scaffolding around the model decides the outcome more than the model does.

Most companies are still hiring for a job that no longer exists at their own company. They write "AI-native" into the job description, put a working agent in front of candidates during the interview — and then, on day one, hand the new hire a stock laptop and a wiki. The harness vanishes the moment the offer is signed.

This piece makes one argument in two halves: provision — give every employee, starting at the interview, a real agent harness; and integrate — stop pretending people don't already bring their own. The governance half of that argument — what you owe once you do it — is its own companion piece: the agent you give your new hire is an identity you've never governed.

The unit of productivity changed under you

For thirty years the unit of knowledge work was a person. You hired the person, measured the person, promoted the person. That unit just got replaced. The new unit is person + harness, and the two are no longer separable. Microsoft's 2025 Work Trend Index gave it a name — the "Frontier Firm," run by teams of humans and agents, where every employee becomes an "agent boss." You cannot make someone a boss and refuse to give them a team. The harness is the team — and once those teammates start transacting with the outside world, they need the same verifiable agent identity any other actor in your systems carries.

SignalNumberSource
Developers using AI tools in their workflow80%Stack Overflow 2025
Code written by Claude at Anthropic70–90%Amodei, 2025–26
PRs shipped in one day by Claude Code's lead (100% agent-written)22Fortune, Jan 2026
Leaders expecting "digital labor" to expand the workforce in 12–18 mo82%Microsoft WTI 2025

What an "agent harness" actually is

An agent harness is the software wrapped around a language model that turns a chat box into a coworker. The field has converged on a clean formula: Agent = Model + Harness. The model reasons; the harness does everything else — tool execution, context and memory, sandboxing, permissions, error recovery, and the project-specific instructions that tell the agent how your shop works. Claude Code, Cursor, Codex, Copilot. The model is a commodity you rent; the harness is the asset you own. The same discipline underwrites our own agent-audit methodology — you can't reason about an agent's output without reasoning about the harness that produced it.

The 34-point proof: In Cursor's own research, the same model scored 46% on one harness and 80% on another on SWE-bench — a 34-point swing from scaffolding alone. Your competitive edge isn't which model you buy. It's the harness you build around it and put in your people's hands. It is exactly why you can't buy agent accuracy with a bigger model.

As the practitioners put it: writing code is cheap now; verification is the expensive part. The harness is where verification lives — the tests, the sandboxes, the review loops. It's the same reason a per-call agent economy needs a receipt for every unit of work, the argument we made in why power users are cancelling their AI subscriptions and built into the auditable proof chains behind every BlindOracle deliverable.

You already interview with the harness — then you take it away

The interview is the first place the contradiction shows. The whiteboard is dead as a signal, and the best companies know it:

CompanyWhat changedWhat they grade now
Meta"AI-Enabled Interviews" — candidates use real models live"Critical verification" — catching AI-introduced errors
CanvaScrapped CS-fundamentals; mandatory AI-assisted codingJudgment on problems you can't one-prompt
ShopifyAI embedded in live interviews; ~90–95% of the taskAI judgment — when to intervene

If the interview assumes an agent harness, the job does too. A company that screens for "critical verification" against a working agent — then onboards the winner onto a bare laptop with a six-week IT queue — has hired for a job that doesn't exist at its own company yet. The signal you selected for is the capability you then strip away. The fix isn't slower onboarding; it's a configured harness on day one, the same way the marketplace onboarding flow hands a calling agent everything it needs to transact from its first request.

Half two: they already brought their own

Provisioning is necessary but not sufficient, because your people didn't wait. "Bring your own AI" isn't a future policy debate — 78% of AI users already bring their own tools to work, 67% of workplace AI interactions happen on personal accounts IT can't see, and over half won't admit to using AI on their most important tasks. The choice was never "allow it or not." Three out of four already did. The real choice is: govern the agents people brought, or stay blind to them — the same trust-an-agent-you've-never-met problem we unpack in trust an agent you've never met.

The cost of not provisioning is not zero — it's $670,000 higher. IBM's Cost of a Data Breach 2025: 1 in 5 organizations suffered a breach tied to shadow AI; those breaches cost $670K more on average; 97% lacked AI access controls; 63% had no AI governance policy at all. A sanctioned harness isn't a perk — it's a firewall. "Integrate" means a standard harness good enough that BYOA happens inside your perimeter, not in a browser tab you'll never audit.

What "give them the harness" looks like in practice

The one-line version: the unit of work is no longer the person — it's the person plus their harness. You already interview with it; stop taking it away. Your people already brought their own; stop pretending they didn't. Provision the harness, integrate what they bring, and govern every agent as the identity it is — or hand your competitor a 34-point head start and a $670K discount on your next breach.

Sources (verify primary links before re-quoting): Karpathy 2025 LLM Year in Review · Fowler/Böckeler — Harness Engineering · Cursor 46% vs 80% (via MindStudio) · Stack Overflow 2025 survey · AI interviews — Meta/Canva/Shopify · IBM Cost of a Data Breach 2025 · Microsoft 2025 Work Trend Index. The "bare laptop" line is original framing, not a quoted exec.

Related reading

Trust, identity, harnesses, and governance for AI agents.

Govern the harness you gave them
BlindOracle overview
How it works
Agent identity & ERC-8004
MASSAT audit methodology
Can't buy accuracy with a bigger model
When agents pay agents
Trust an agent you've never met
30-agent proof run
Auditable AI proof chains
Self-audit report
Technical blog