{"slug": "show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp", "title": "Show HN: Spendict – a performance marketer's verdict for AI agents, over MCP", "summary": "Spendict launches a deterministic AI tool that evaluates advertisements before any budget is spent, providing a run, fix_first, or kill verdict based on performance marketing expertise. The tool integrates via MCP, CLI, or REST and aims to reduce ad-spend waste by scoring hooks, angles, audience fit, and compliance against platform rules.", "body_md": "A deterministic run / fix_first / kill verdict for every ad — before you spend on it, not after.\n\nMCP · CLI · Skill · REST · 100 free verdicts · about a penny a call after\n\n“Cut your ad-spend leak in 30 days.”\n\n“Unlock the AI advantage today ✨”\n\n“Founders: your CAC is lying to you.”\n\n“The #1 secret marketers don't want you to know”\n\n“We saved a DTC brand $42k in Q3.”\n\n“Meta CPMs up 34%. Here's what still works.”\n\n“Try our platform. It's really good.”\n\n“Your PMax is fighting your Search. Fix it.”\n\n“Stop A/B testing headlines. Start testing offers.”\n\n“Scale to $1M/mo with one weird trick”\n\nthe whole batch, no cherry-picking — 3 run · 3 fix_first · 4 killed before a cent of spend\n\nDrop in the Skill and your agent gates every ad automatically — or wire it up over MCP, the CLI, or plain REST. Same four tools, same verdict, same quota.\n\nSame SKILL.md works in Claude Code, Cursor, Codex, and Gemini.\n\n```\nnpx skills add spendict/skills\n```\n\nThe skill calls Spendict over MCP or the CLI — connect once (see the MCP or CLI tab).\n\nYour agent now gets a run / fix_first / kill on every ad before it recommends launching.\n\nFour tools, one deterministic verdict each. The budget only moves on ads that earned it.\n\nScores hook, angle, clarity, audience fit, platform fit, CTA, and compliance — and names the single predicted failure mode before a cent is committed.\n\nBudget allocation, audience setup, bid strategy, measurement — checked against each platform's actual rulebook, before the structure fragments your spend.\n\nFeed it live metrics and it separates creative fatigue from structural problems — instead of guessing which lever to pull.\n\nGive it the product and the goal; it returns a structure-validated targeting strategy your agent can build from directly.\n\nThe judgment inside comes from performance marketers with 10+ years in paid social — they directed the model's development and calibrated every verdict against real ads.\n\nSix AI-generated ad hooks, scored by the same engine that grades yours — each with the predicted failure mode attached, not just a number.\n\n“Unlock the AI advantage today ✨”\n\nZero specificity, generic AI puffery\n\n“I switched from boosting posts to this and finally stopped guessing.”\n\nNamed pain plus concrete outcome\n\n“Stop guessing. Start scaling your ad spend with confidence.”\n\nVague CTA, no proof point\n\n“The future of marketing is here.”\n\nNo product, no audience, no hook\n\n“3 signs your Meta campaign is bleeding budget (and how to fix #2 today)”\n\nSpecific plus curiosity plus a real fix\n\n“Transform your business with our revolutionary platform.”\n\nBuzzword salad, zero mechanism\n\nFour guardrails baked into every call — not settings you have to remember to turn on.\n\nStreamable HTTP — works in Claude, Cursor, Windsurf, n8n out of the box.\n\nSame verdicts, same key — one-for-one REST endpoints for any other stack.\n\nEvery key is hashed server-side; bearer-token auth on every call.\n\nA maxed-out key never triggers a model call — and failed calls are refunded.\n\nReal performance reconciles against the tool's own earlier pre-flight call.\n\nMarketers with 10+ years in paid social directed the model's development — real ads, not scraped trend data.", "url": "https://wpnews.pro/news/show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp", "canonical_source": "https://www.spendict.com/", "published_at": "2026-07-12 10:02:33+00:00", "updated_at": "2026-07-12 10:05:04.138176+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-products"], "entities": ["Spendict", "Meta", "Claude Code", "Cursor", "Codex", "Gemini"], "alternates": {"html": "https://wpnews.pro/news/show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp", "markdown": "https://wpnews.pro/news/show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp.md", "text": "https://wpnews.pro/news/show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp.txt", "jsonld": "https://wpnews.pro/news/show-hn-spendict-a-performance-marketer-s-verdict-for-ai-agents-over-mcp.jsonld"}}