Blog→AI Economics
AI Economics7 min read read

Claude Search Fails: Prompting Kills Adoption

Why your Claude-powered search tool has zero adoption: Prompt engineering creates workflow friction, not value. Learn how AI features become operational liabilities.

By Richard Ewing·
Share:

Claude Search Fails: Prompting Kills Adoption

You approved the budget for a generative search feature, your engineering team delivered a technically flawless product, and your telemetry now shows a usage graph that is completely flat. The capital expenditure has successfully converted into an ongoing operational liability.

Across the enterprise software sector, organizations are discovering that integrating advanced large language models into legacy platforms is creating an unsustainable misalignment between product value and compute cost. When you build features that require users to engineer prompts just to retrieve their own data, you are not delivering an operational advantage. You are actively degrading their workflow while paying premium API rates for the privilege.

Like this analysis?

Get the weekly engineering economics briefing — one email, every Monday.

Subscribe Free →

More in AI Economics

Your AI Coding Tools Are a $58K/Engineer Maintenance Liability — Not a Productivity Gain

GitHub Copilot just moved to usage-based billing. METR proved devs are 19% slower with AI — while feeling 24% faster. That perception gap is costing you $58K per engineer per year in hidden maintenance, security debt, and verification overhead. Here is the math your vendor will never show you.

14 min read

Your Claude API Bill Is Destroying Your Margins — The Economics of Model-Task Mismatch

Enterprise teams are using frontier models for simple tasks and watching margins evaporate. Here is how to calculate your cost collapse point and implement tiered inference routing.

6 min read

The Rise of the AI Economist: Why Product Managers Must Evolve or Perish

Traditional software has zero marginal cost. AI features carry massive, compounding variable costs. If product managers don't learn to engineer margins, they will bankrupt their companies.

8 min read

Related Canonical Concepts

AI Volatility Tax

The compounding gross margin penalty incurred when variable LLM inference query costs scale faster than subscription revenue, shifting server hosting into variable Cost of Goods Sold (COGS).

Read Concept →

Deterministic Governance

The architectural pattern enforcing hard-coded, code-level execution gates and state verification outside the probabilistic LLM inference loop.

Read Concept →

The Subprime Code Crisis

The systemic financial risk created when high-velocity AI code generation produces massive volumes of un-audited, low-trust technical debt that inflates future maintenance liabilities.

Read Concept →

AI Governance

The enterprise control framework governing security, compliance, operational boundaries, and audit trails for autonomous AI models and multi-agent workflows.

Read Concept →

Inference Economics

The financial discipline of managing, projecting, and optimizing the per query token costs associated with running large language models in production.

Read Concept →

Canonical Frameworks

Innovation Tax

The Innovation Tax is the hidden cost of maintenance work that gets reported as innovation investment. It is OpEx masquerading as R&D investment, causing organizations to dramatically overestimate their effective engineering velocity and R&D productivity. Here's how it works: A VP of Engineering reports to the CEO that "65% of engineering time is spent on new features." The actual breakdown, when forensically audited, reveals that only 23% of engineering time produces genuine new capabilities. The remaining 42% is maintenance work embedded within feature sprints — bug fixes bundled into feature stories, infrastructure upgrades coded as dependencies, and refactoring disguised as feature prerequisites. This 42-point gap between reported and actual innovation investment is the Innovation Tax. It's not fraud — it's systematic self-deception enabled by the way agile teams organize work. When a sprint contains 10 stories and 4 of them are technical debt cleanup dressed as "tech stories" within a feature epic, the team genuinely believes they're spending 100% on features. The Innovation Tax is insidious because it compounds. As the maintenance burden grows quarter-over-quarter, the tax increases. But because teams don't measure it, CFOs and boards continue to believe R&D spending is generating proportional innovation output. By the time the gap becomes visible (missed deadlines, slow feature delivery, competitive lag), the organization is often approaching the Technical Insolvency Date. Benchmarks from Richard Ewing's audits show that most engineering organizations have an Innovation Tax between 30-50%. Organizations with Innovation Tax above 40% are in dangerous territory. Above 70% is terminal — the organization is approaching technical insolvency within 4-6 quarters.

Read Definition →

Kill Switch Protocol

The Kill Switch Protocol is a structured framework for identifying and deprecating "Zombie Features" — code that requires ongoing maintenance but generates zero incremental business value. Most software organizations have a dangerous bias: they add features but never remove them. Product teams celebrate launches. Nobody celebrates deletions. Over time, this creates what Richard Ewing calls "feature gravity" — a constantly growing codebase where 40-60% of the code serves no active users and generates no measurable revenue, yet still consumes engineering maintenance hours. Zombie features come in several varieties: - **Ghost Features**: features that were built, launched, and never adopted. They sit in the codebase, requiring maintenance, but have near-zero usage. - **Legacy Bridges**: compatibility layers, deprecated API versions, and backward-compatible code paths that serve a tiny percentage of users but add complexity to every future change. - **Vanity Features**: features built because a senior stakeholder wanted them, not because users needed them. Often protected by organizational politics rather than business merit. - **Abandoned Experiments**: A/B test variants that were never cleaned up, prototypes that became permanent, and "temporary" solutions that became load-bearing. The Kill Switch Protocol provides a systematic approach to identification, evaluation, and deprecation: 1. **Identify**: Flag features with less than 5% of peak usage, zero revenue attribution, or maintenance cost exceeding 10% of the feature's value contribution. 2. **Quantify**: Calculate the total cost of keeping each zombie alive (maintenance hours × fully-loaded engineer cost × opportunity cost multiplier). 3. **Assess Risk**: Evaluate deprecation risk — what breaks if this feature is removed? What customers are affected? 4. **Sunset Timeline**: Create a communication plan and graduated deprecation (warning → deprecation notice → feature flag → removal). 5. **Execute**: Remove the code with rollback capability. Monitor for unexpected breakage. The typical Kill Switch audit reveals that 30-50% of maintenance burden comes from zombie features. Removing them frees up 15-25% of engineering capacity for actual innovation.

Read Definition →
📊

Richard Ewing

The AI Economist — Quantifying engineering economics for technology leaders, PE firms, and boards.

Book Advisory →Curriculum →Free Tools →

Keep exploring

blog

Data Pipeline Cost Optimization

comparison

AUEB vs. AWS Cost Explorer

comparison

Claude Code vs. Cursor Governance

← Back to Blog
⚡

Want to apply this to your organization?

Run a free diagnostic first. If the numbers concern you, book a session to build a remediation plan.

Run Free Diagnostic (Free)View Advisory Options

Richard Ewing — AI Economist & Capital Auditor