ADD Across the Org: AI-Driven Development Beyond Code

In this series

1. 1 ADD Beyond Code: Applying AI-Driven Development Outside Engineering 11 min read

   AI-Driven Development was born in software, but the method is domain-independent. The producer is now an AI in every knowledge-work domain — so the same loop applies: constrain the what, free the how, verify by evidence. The framework for the whole series.

2. 2 ADD for Marketing: Briefs as Specs, Brand as the Frozen Contract 11 min read

   AI floods marketing with on-brand-looking copy that is off-strategy. ADD fixes it: the brief is the spec (with named refusal reasons), brand and claims are the frozen contract, the A/B test is verification by evidence, and performance folds into a living playbook.

3. 3 ADD for Sales: Clamp the ICP, Free the Outreach 13 min read

   AI can flood prospects with personalized-looking outreach that is off-ICP, mis-priced, or non-compliant. ADD clamps the what — ICP, claims, pricing authority — and frees the how, then verifies by reply and win rates instead of by how persuasive the copy reads.

4. 4 ADD for Customer Support: Killing Confident Wrong Answers 10 min read

   AI support drafts are fluent and frequently wrong — invented policy, steps that don't exist. ADD makes the source-of-truth the contract, factuality-against-source the red test, and a measured hallucination rate the evidence — so confident wrong answers are caught before they reach a customer.

5. 5 ADD for HR: Rubrics as Specs, Calibration as the One Gate 11 min read

   AI screening reads objective and can be quietly biased. ADD makes the calibrated rubric the frozen contract, a gold-set plus counterfactual bias probes the red tests, and adverse-impact tracking the evidence — so a human, never the model alone, owns every decision about a person.

6. 6 ADD for Project Management: Exit Criteria Over Status Theater 12 min read

   AI can generate plans and status that look complete while the goal is unmet. ADD makes evidence-backed exit criteria the contract, the dynamic goal-loop the engine, and an artifact — not a self-reported 'green' — the proof a milestone is actually done.

7. 7 ADD for Engineering Leadership: Owning Direction and Verification 13 min read

   When agents and teams produce more than any leader can read, line-by-line review collapses. ADD reframes the job: the ADR and its fitness functions are the frozen contract, fitness checks are the red tests, and production evidence — not a clean diagram — is how direction is verified.

8. 8 ADD for DevOps and SRE: Policy as Contract, Evidence as the Gate 11 min read

   AI can emit Terraform and runbooks that read correct and provision the wrong, insecure, or irreversible thing. ADD makes policy-as-code the frozen contract enforced in the pipeline, chaos and rollback tests the red tests, and SLO evidence — not a clean apply — the proof a change is safe.

9. 9 ADD for Machine Learning: The Eval Set Is the Frozen Contract 14 min read

   ML is AI building AI, and a high headline metric hides leakage, gamed proxies, and slice regressions. ADD locks the eval set, thresholds, and model card as the frozen contract, makes the held-out suite the red tests, and verifies by slices and online evidence — not by the leaderboard number.

10. 10 ADD for Finance and FP&A: Lock the Assumptions, Prove the Forecast 15 min read

    An AI-built model reconciles at a glance and hides a broken assumption or a double-count. ADD locks the assumption set as the frozen contract, makes reconciliation and integrity checks the red tests, and verifies by backtest against actuals — not by whether the numbers look reasonable.

11. 11 ADD for Legal: Contract-First, Literally 12 min read

    Legal is where ADD maps most literally — the negotiation playbook is the frozen contract. AI drafts and redlines read authoritative and can quietly concede a material term; ADD makes playbook-conformance the red test and an adversarial redline the evidence, with off-playbook concessions a hard stop.

12. 12 ADD for Compliance and Risk: Named Violations, Frozen Controls 13 min read

    Compliance is where ADD's gates fit most naturally. AI control documentation reads thorough and can map to nothing real; ADD names every violation, freezes the control framework, makes control tests the red tests, and treats every finding as a hard stop.