Loading page…
Company intelligence / Live profile
Track LangChain's role in the AI economy through Superpower Daily reporting on tools, business, and models. This live company page updates automatically as new launches, partnerships, product moves, and market signals are published.
Key developments
AI Search uses a model to check session records against plain-language questions. Its fixed reading budget favors conversations over tool output.
The integration summarizes history, compresses tool results and extracts fields. ScaleDown’s speed and cost claims come from its own benchmarks.
The partnership builds on DXC’s existing OASIS platform. DXC reports sharp reductions in incident-resolution time, while sensitive actions can pause for human approval.
Managed Deep Agents v0.9 runs scheduled work with the requester’s permissions and lets developers choose models and tools before each run.
The Deep Agents update also lets apps preload selected skills and refresh ongoing conversations. Keeping cached prompts intact depends on the model and the operation.
A 973-thread experiment found no statistically significant difference in code-merge outcomes. But its router commits to one model before a conversation unfolds.
A browser-action test also cut median latency. Both workflows reserve language models or people for decisions the faster model cannot handle alone.
Version 0.8 also lets agents receive Slack files and web requests. Its built-in search is limited to two LangSmith plans.
Connected coverage
Your company watchlist
product
