Pinned Tweet
Introducing Tenet, our first model post-trained for legal.
Tenet is a Kimi K3 base that we post-trained with @FireworksAI_HQ on a corpus of publicly available legal data, synthetic data, and human expert data simulating long-horizon legal work.
Training increases Tenet's all-pass rate by 82% on LAB and 22% on LAB Contracts relative to the Kimi K3 base model. It achieves state-of-the-art performance on LAB Contracts and places second on LAB.
These gains generalize to other leading agentic benchmarks including @mercor's Apex Agents - Corporate Law, @crosbylegal's Redline Bench, and @scale_AI's Professional Reasoning Bench.
Tenet is also optimized for token efficiency, operating at less than a fourth the cost of leading foundation models.
We additionally post-trained three specialist models for Tenet to use as subagents:
1) M&A Diligence: post-trained with @baseten on our LAB Diligence environment in an RLM harness, this model is optimized for high-scale, long-horizon tasks.
2) Review Tables: trained with @appliedcompute on our Review Table environment, this model is state-of-the-art and cost-effective at high-volume document review and structured data extraction.
3) Firm Knowledge: trained with @EngramLab on our synthetic law firm environment, this model is optimized to learn and search over a firm's knowledge via memory and structured notes.
More details on model training, environment design, benchmarking, results, and more in the article by @gabepereyra below.
What's next for Harvey’s research?
- Scaling LAB to more jurisdictions, practice areas and workflows
- Scaling compute to bring new generalist models and capabilities to Harvey
More to come soon.
Tenet is a Kimi K3 base that we post-trained with @FireworksAI_HQ on a corpus of publicly available legal data, synthetic data, and human expert data simulating long-horizon legal work.
Training increases Tenet's all-pass rate by 82% on LAB and 22% on LAB Contracts relative to the Kimi K3 base model. It achieves state-of-the-art performance on LAB Contracts and places second on LAB.
These gains generalize to other leading agentic benchmarks including @mercor's Apex Agents - Corporate Law, @crosbylegal's Redline Bench, and @scale_AI's Professional Reasoning Bench.
Tenet is also optimized for token efficiency, operating at less than a fourth the cost of leading foundation models.
We additionally post-trained three specialist models for Tenet to use as subagents:
1) M&A Diligence: post-trained with @baseten on our LAB Diligence environment in an RLM harness, this model is optimized for high-scale, long-horizon tasks.
2) Review Tables: trained with @appliedcompute on our Review Table environment, this model is state-of-the-art and cost-effective at high-volume document review and structured data extraction.
3) Firm Knowledge: trained with @EngramLab on our synthetic law firm environment, this model is optimized to learn and search over a firm's knowledge via memory and structured notes.
More details on model training, environment design, benchmarking, results, and more in the article by @gabepereyra below.
What's next for Harvey’s research?
- Scaling LAB to more jurisdictions, practice areas and workflows
- Scaling compute to bring new generalist models and capabilities to Harvey
More to come soon.
121
288
3,088
3,568,003
Harvey is now FedRAMP Class D (High) certified.
U.S. federal agencies, contractors, and partners can now use Harvey for legal work in an environment built for sensitive government information.
Read the announcement: link.harvey.ai/uucoF
U.S. federal agencies, contractors, and partners can now use Harvey for legal work in an environment built for sensitive government information.
Read the announcement: link.harvey.ai/uucoF
0
2
3
407
Horizon Scanning is now available in Harvey.
Monitor 11,000+ legislative and regulatory primary sources across 100+ jurisdictions in one feed.
See the developments most relevant to your business first, tagged by topic, jurisdiction, and date.
Draft emails, memos, and briefings se scans in Assistant, agents, and Spaces.
Monitor 11,000+ legislative and regulatory primary sources across 100+ jurisdictions in one feed.
See the developments most relevant to your business first, tagged by topic, jurisdiction, and date.
Draft emails, memos, and briefings se scans in Assistant, agents, and Spaces.
5
5
44
5,964
Review Tables now load up to 5.8x faster in Harvey.
Our engineering team built server-side pagination to support larger reviews without loading the entire table into browser memory.
That required:
- A Turbopuffer query layer for server-side sorting and filtering
- Custom row-ID oading
- Typed and string fields to handle inconsistent model outputs
- Fallback reads and backfill jobs to recover from data drift
Our engineering team built server-side pagination to support larger reviews without loading the entire table into browser memory.
That required:
- A Turbopuffer query layer for server-side sorting and filtering
- Custom row-ID oading
- Typed and string fields to handle inconsistent model outputs
- Fallback reads and backfill jobs to recover from data drift
7
2
127
8,663
Read our engineering blog on scaling Review Table UI: harvey.ai/blog/making-re…
0
0
5
878
Harvey retweeted
Curious how @harvey makes hundreds of tailored demo videos?
Through Figma’s MCP, agents work directly on the canvas to:
→ Pull in visual context from their brand and motion guidelines designed in Figma
→ Storyboard and animate using Figma Motion, for review and feedback with their team
→ Generate imagery and video with @figmaweave
Through Figma’s MCP, agents work directly on the canvas to:
→ Pull in visual context from their brand and motion guidelines designed in Figma
→ Storyboard and animate using Figma Motion, for review and feedback with their team
→ Generate imagery and video with @figmaweave
How @ShawnFarsai uses @figma @ElevenLabs and @claudeai to create hyper personalized marketing videos with agents x.com/i/article/2112…
18
31
328
40,782
Harvey retweeted
Awesome to see @ShawnFarsai and @gabepereyra share Harvey's work around combining agentic workflows with the Figma canvas and Weave!
Excited to make this something you can do end to end in Figma! (We're so close!)
Excited to make this something you can do end to end in Figma! (We're so close!)
How @ShawnFarsai uses @figma @ElevenLabs and @claudeai to create hyper personalized marketing videos with agents x.com/i/article/2112…
10
16
217
20,792
Harvey retweeted
how to channel your ai psychosis and creativity into arr featuring @figma and @ElevenLabs
How @ShawnFarsai uses @figma @ElevenLabs and @claudeai to create hyper personalized marketing videos with agents x.com/i/article/2112…
5
2
39
3,445
How Harvey's marketing org is using @figma, @ElevenLabs and @claudeai to:
- Create entire launch films with agents
- Build tailored demo videos for each customer using sales calls and account insights
- Script and voice hundreds of films overnight
While burning 15 billion tokens over 2 weeks.
Deep dive by @gabepereyra and @ShawnFarsai:
- Create entire launch films with agents
- Build tailored demo videos for each customer using sales calls and account insights
- Script and voice hundreds of films overnight
While burning 15 billion tokens over 2 weeks.
Deep dive by @gabepereyra and @ShawnFarsai:
How @ShawnFarsai uses @figma @ElevenLabs and @claudeai to create hyper personalized marketing videos with agents x.com/i/article/2112…
5
6
143
16,473
Harvey retweeted
@JensenHuang at GTC:
"Here's Trajectory and Harvey using Nemotron, post-trained it and created their own frontier-level capability."
"With customization and with partners in the ecosystem that we work with, you could turn these models into the frontier.
And a result, turn nto sovereign intelligence"
It's great to be doing work with such amazing companies like @harvey and @nvidia over here at @trajectorylabs!
"Here's Trajectory and Harvey using Nemotron, post-trained it and created their own frontier-level capability."
"With customization and with partners in the ecosystem that we work with, you could turn these models into the frontier.
And a result, turn nto sovereign intelligence"
It's great to be doing work with such amazing companies like @harvey and @nvidia over here at @trajectorylabs!
24
27
191
16,931