Eric does things.

Human in the loop. AI in the driver's seat. Me with the emergency brake.

๐Ÿ“  ericdoes.web.app ยท ericdoes.pages.dev ยท last updated

Hi, I'm Eric Yim. Everything here is a joint venture between me and an AI.

The workflow is simple: the AI spews fast, remarkably confident nonsense; I catch it red-handed, fix the citations it completely made up, and sign off before anything hits production.

To sum it up: It brings the typing speed. I bring the adult supervision.

If you spot a bug or a hallucination wearing a tuxedo, that's on me โ€” the AI tried its best to gaslight me, and I fell for it.

Archive ยท newest first

  1. Beisen โ€” pricing evidence and a quote worksheet HTML report

    Re-audited pricing research: a qualified official reference, source-by-source evidence limits, a quote-based calculator that preserves unknown costs, and an explicit correction of unsupported implementation fees and total budgets.

  2. Can a creator authorize automatic access to Xiaohongshu content data? Feasibility brief

    A business-facing answer to a simple product question: even with the creator's consent, the proposed automatic sync cannot currently be built through Xiaohongshu's public platform. Here is what is blocked, why consent alone is insufficient, and the three realistic paths forward.

  3. From personal expertise to a reliable Skill ร— SOP system Research report

    A practical, evidence-driven guide to turning tacit expertise into a repeatable service: validate the expert, capture decisions with ACTA/CDM, model service flow and rules, design data and tool contracts, then operate the Skill with permissions, idempotency, evals, SLOs, versioning, and rollback. Includes a 0โ€“9 lifecycle, 90-day plan, 12-artifact MVP, templates, test matrix, and 30 source entries.

  4. Nowcoder โ€” how a free coding community makes its money, end-to-end HTML report

    Business-model teardown of Nowcoder: a free coding-prep community of 10M+ students monetized through three B2B layers โ€” resume sourcing (>50% of revenue), pay-per-use exam/interview SaaS, and employer-brand ads. 59 sourced references, 2025โ€“2026 procurement records (incl. a ยฅ1.45M contract from a central-bank-affiliated fintech), an AI-agent pivot timeline, and honest notes on which metrics stopped updating after 2023โ€“2024. ~2,800 lines, no tracking, no JS beyond Chart.js.

  5. Mercor โ€” $20B in 2.5 years, end-to-end HTML report

    Investment-research teardown of Mercor's 5-round, 100ร— valuation jump from a $194M seed to a pending $20B post-money. 25 sourced references, 6 findings (capital pacing, revenue curve, supply-side scale, margin trajectory, market reputation, valuation re-rating), plus an honest limitations section and methodology. ~2,700 lines, no tracking, no JS beyond Chart.js.

  6. Jack & Jill โ€” $20M seed round, end-to-end HTML report

    Investment-research teardown of Jack & Jill's Creandum-led $20M seed. 27 sourced references, 7 findings (cap stack, moat, and a side of healthy skepticism), charts, and an honest limitations section. ~2,100 lines, no tracking, no JS beyond Chart.js.