Studio Founder
Flagging Non-Standard Clauses in an Investment Agreement β In 2 Minutes
Key Takeaway
Our AI agent benchmarks every clause in a term sheet against market standards and flags non-standard or aggressive terms before you even call the lawyer.
The Problem
Series A negotiation. Thursday evening. Lead investor sends a 42-page shareholders' agreement. The partner call is Monday morning.
Your options: pay a lawyer β¬8K for an emergency weekend review. Or read it yourself and pretend you understood the full ratchet anti-dilution buried on page 31.
Neither option is good. The first is expensive. The second is dangerous.
Here's what actually happens at most startups: the founder skims the term sheet, Googles "is 2x liquidation preference normal" at midnight, and walks into the negotiation half-prepared. The investor's lawyer drafted the document. They know exactly which clauses are aggressive. You don't.
That information asymmetry costs founders millions. Not in legal fees β in equity they gave away because they didn't know a clause was non-standard.
The Solution
The Contract Analyzer skill on Mr.Chief. Upload any term sheet, SHA, or investment agreement. The agent benchmarks every material clause against a database of market-standard terms drawn from 500+ French and European venture deals.
Output: an annotated document where every clause is tagged STANDARD, NON-STANDARD, or AGGRESSIVE β with the reasoning and market comparison for each.
You don't replace the lawyer. You walk into the lawyer call already knowing which 5 clauses to fight about.
The Process
yamlShow code
# mrchief skill: contract-analyzer
# Upload the SHA and run clause analysis
task: "Analyze this shareholders' agreement against market standards for a French Series A (β¬3-8M range)"
input: ./documents/sha-series-a-draft.pdf
benchmark: eu-venture-2020-2025
jurisdiction: france
output_format: annotated-markdown
The agent parses the document into clause categories:
View details
Clause Categories Analyzed:
βββ Liquidation Preference β 1.5x non-participating [NON-STANDARD β οΈ]
βββ Anti-Dilution β Full ratchet [AGGRESSIVE π΄]
βββ Drag-Along β 60% threshold [NON-STANDARD β οΈ]
βββ Tag-Along β Pro-rata, all classes [STANDARD β
]
βββ Board Composition β 2 founder, 2 investor, 1 independent [STANDARD β
]
βββ Vesting Acceleration β Double trigger, 100% [NON-STANDARD β οΈ]
βββ Founder Lock-Up β 4 years [AGGRESSIVE π΄]
βββ Information Rights β Monthly + observer seat [STANDARD β
]
βββ Pre-Emption Rights β All shareholders, 30 days [STANDARD β
]
βββ Non-Compete β 36 months, all sectors [AGGRESSIVE π΄]
βββ Good/Bad Leaver β Cliff at 12 months [STANDARD β
]
The scoring methodology:
View details
Benchmark Database:
- 500+ term sheets (2020-2025)
- Segmented by: round size, geography, sector
- Sources: anonymized deal data, published market reports (BVCA, France Invest, Index Ventures)
Scoring:
- STANDARD: clause falls within P25-P75 of market distribution
- NON-STANDARD: clause falls outside P25-P75 but within P10-P90
- AGGRESSIVE: clause falls outside P10-P90 β investor-favorable outlier
Each tag includes:
- Market median for comparison
- Percentile rank of the proposed term
- Specific risk explanation
- Suggested counter-proposal language
For the full ratchet anti-dilution:
View details
π΄ AGGRESSIVE: Full Ratchet Anti-Dilution
Proposed: Full ratchet
Market median: Broad-based weighted average
Percentile: P3 (97% of deals use weighted average)
Risk: In a down round, full ratchet converts at the lower price
regardless of round size. A small bridge round at 50% discount
would nearly double investor ownership.
Suggested counter: "Broad-based weighted average anti-dilution,
with carve-outs for employee option pool top-ups up to [X]%."
The Results
| Metric | Before | After |
|---|---|---|
| Time to first clause review | 3-5 days (lawyer) | 2 minutes |
| Cost per agreement review | β¬5,000-β¬8,000 | ~β¬0.30 (API cost) |
| Non-standard clauses identified | Depends on lawyer's attention | 100% coverage, every clause |
| Negotiation preparation time | 1 weekend of Googling | 15 minutes reading the report |
| Clauses pushed back on (Series A) | 1-2 (founder guessing) | 4 (data-backed) |
| Estimated equity saved | Unknown | ~0.8% (anti-dilution + leaver terms) |
The real number: 0.8% equity at a β¬20M post-money valuation is β¬160,000. The agent cost β¬0.30 to run.
Try It Yourself
bashShow code
mrchief run contract-analyzer \
--input ./your-term-sheet.pdf \
--benchmark eu-venture-2020-2025 \
--jurisdiction france
Works with: term sheets, SHAs, convertible notes, SAFEs, side letters. French, English, or bilingual documents.
The agent doesn't replace your lawyer. It makes your lawyer faster and makes you a better negotiator.
Every clause you don't flag is a clause you accepted. Know the market before the market knows you don't.
Related case studies
Studio Founder
Comparing Two Contract Versions in 30 Seconds β Every Change Highlighted
When an investor sent back a revised term sheet, our AI agent diffed it semantically in 30 seconds β flagging who benefits from each change, not just what changed.
Studio Founder
Preparing Share Transfer Documents β Stock Transfer in 20 Minutes
We generate ordre de mouvement, certificat de cession, and registre des mouvements in French SAS format β handling prΓ©emption and agrΓ©ment procedures β in 20 minutes instead of 2 weeks.
Studio Founder
Auto-Formatting Board Minutes That Actually Pass Legal Review
We feed rough meeting notes into an AI agent and get back properly formatted French board minutes β procΓ¨s-verbal with numbered resolutions, quorum verification, and legal language β in 5 minutes.
Want results like these?
Start free with your own AI team. No credit card required.