Our team at @fieldguide spoke at AI Engineer New York this week, walking through how we engineer systems for defensible agent decisions.
We shared a version of the talk on our engineering blog: https://t.co/IwjVTZzK4G
Sharing more this week about how our design team at @fieldguide works. We have a culture here where designers can ship, not just hand off prototypes.
Our design and development process is designed to compress every step. Our software factory means design creates high-fidelity product concepts that work in our actual codebase. It also means small customer improvements often get same-day turnarounds vs. waiting for prioritization.
https://t.co/JKMiG7QS8K
How do you audit an audit agent? Our AI team wrote up how we do it at @fieldguide.
Agent evals are very different from model evals. The combo of the harness, context, tools, and model creates a different set of challenges. We find that firm-specific context skews results the most.
We solve this with our context graph, Agent Knowledge, which lets agents understand a firm's historical corpus of data. This ensures that the agent retrieves details the firm actually cares about instead of reasoning from a generic standard.
Read more: https://t.co/rgx08NdmOV
Long-horizon agents create a unique set of challenges with evals. Today's @fieldguide engineering blog covers our framework for running long-horizon agent evals at scale.
Our framework runs agents and simulates the human side of the conversation, then scores the results. Each session runs in its own sandboxed workflow, so we can run many in parallel and check consistency across runs. Anyone on our team can propose a change to agent behavior, launch a batch of tests, and come back with evidence about whether it worked.
Read more: https://t.co/L5aq8hBzK9
This week we're sharing technical deep dives on Field Orchestrator, our multi-agent system behind audit workflows at @fieldguide.
Today's post covers how our harness and top-level agent, as we split a workflow into units of work that run in parallel and delegate them to specialized sub-agents while holding the high-level state: https://t.co/PyZa57SR5x
Fieldguide has raised a $17M Series A led by @8vc , with participation from @floodgatefund ,@AICPA /cpa.com, and other strategic investors. This new capital will fuel our growth to fundamentally impact the assurance & advisory industry.
Learn more here: https://t.co/R26GK1Pybh
🎉 Congratulations to our CEO, @JinChang for being named to @cpapracadvisor's 2021 20 Under 40 Influencers! The @Fieldguide team is honored to be recognized as a key innovator for the assurance and advisory industry.
#riskadvisory#riskassurance
https://t.co/1N5uS26XIj
San Francisco's Shared Spaces program has kept your favorite restaurants alive and your neighbors employed. Outdoor dining has transformed our streets into communities. Sign our petition to make this temporary program permanent!
https://t.co/bNuamwR0rd
🎉 Today, we’re excited to officially announce the launch of Fieldguide, a new automation and collaboration platform for assurance and advisory firms.
Risk practitioners power trust for capital markets and businesses–but software for professionals hasn't kept up with the times.
Homelessness in America is usually written in pieces—this experience, that cause, such aid—but that’s not the nature of the problem or its intractability. In this week’s @NewYorker, I look at the ecosystem as a whole, focussed on one city: San Francisco. https://t.co/kHL4HUSATs
Transportation accounts for nearly a third of total greenhouse gas emissions in the US, and more than half of that is from cars. The modern American city is designed to favor cars and make other ways of getting around suck.
It’s time we changed that 6/ https://t.co/7RknEfZrRp
1/ We recently released a suite of new features on our tech #platform to help clients better collaborate with their #legal team & manage their legal needs. BTS, it supercharges our #attorneys, #paralegals, etc. w/ custom tools that enable them to provide great service to clients.