Decision Platform
Syntheos (internal platform)
Deepfield: a modular assessment platform
An eleven-stage strategic assessment pipeline that turns a query into a defensible course of action with full evidence lineage.
See the engagementDecision systems
that survive an audit.
Syntheos designs and ships working platforms for federal R&D funders, defense leaders, research institutions, and universities. Every conclusion traces back to its source. Our systems run today at DARPA program offices, the Andrew W. Marshall Foundation, and Georgetown.
Each engagement ends with a working system your team runs. Not a deck that ages out in ninety days.
Scroll
0M+Publications Indexed
Bibliometric coverage of the global scientific literature.
0+Verified Claims
Every quantitative claim on every Syntheos site is backed by a reproducible source query. Open the ledger and the number reproduces live.
0+Peer-Reviewed Publications
Authored by the Syntheos team across science mapping, decision intelligence, computer science, and research evaluation.
0Black Boxes
Every output traces to source evidence through W3C PROV lineage. No opaque models. No silent fallbacks.
Trusted by leaders in defense, healthcare, research, and public policy
Work
Systems we've shipped.
Every engagement ends with a working system, not a slide deck. These four are the canonical example of each archetype we build. See all our work for the full portfolio.
Program Analysis Product
DARPA program offices
DARPA program analysis sites: evidence you can audit
Per-program analytical sites where every quantitative claim is backed by a reproducible query and a confidence level.
See the engagement
Research Intelligence Tool
Andrew W. Marshall Foundation
The Marshall archive: making a hidden corpus navigable
A knowledge-graph research console that opens Andrew Marshall's Office of Net Assessment tradition to a new generation of strategists.
See the engagement
Human-AI Teaming System
Georgetown School of Foreign Service (SEST)
Georgetown Wicked Problems Lab: a classroom where AI assists but never decides
A deployed teaming platform where an AI orchestrator dispatches specialized agents, but phase gates and a delegation contract keep every real judgment in student hands.
See the engagementGovernment & DefenseBuilt for federal
Built for federal
acquisition.
Decision intelligence systems designed from the ground up for classified environments, Congressional oversight, and the DoD AI mandate. We speak your language because we've done this work.
View Defense CapabilitiesSAM.gov RegisteredNIST 800-171 In ProgressDFARS 7012 In ProgressResponsible AI by Design
Past Performance
DARPA, CSET, Marshall Foundation, Noble Reach
Mission Areas
Competitive Assessment, Technology Scouting, Decision Architectures
Acquisition Pathways
Direct Award, OTAs, BAAs, CSOs, Subcontractor on Major IDIQs
What we build
Four shapes of
working system.
Different decisions need different infrastructure. These are the four shapes we build well, each one grounded in a system we've already shipped.
01
Program Analysis Products
Fixed-scope analytical sites where every quantitative claim ships with a reproducible query and a confidence level. Built for R&D funders who have to defend portfolio decisions on the record.
Proof: DARPA program offices
- Deployed analytical site, one per program
- YAML evidence ledger behind every claim
- Reproducible SQL queries against your warehouse
- Python refresh pipeline for standing data
02
Decision Platforms
An eleven-stage assessment pipeline you run yourself. Every stage carries W3C PROV lineage, so any final recommendation traces back through the whole chain to the source evidence. Built for standing net-assessment and competitive-intelligence work.
Proof: Deepfield
- Modular pipeline, eleven stages, tuned to your domain
- Knowledge graph, ACH-based reasoning, wargaming
- Adaptive compute budgets per stage
- Full evidence lineage on every recommendation
03
Research Intelligence Tools
Knowledge-graph research consoles over specialist corpora. Hybrid retrieval, chat with citation badges, and a visual distinction between verified archive material and AI-generated inference. Built for institutions that want researchers to think with a corpus, not just read it.
Proof: Andrew W. Marshall Foundation
- Knowledge graph built from your documents
- Hybrid vector, full-text, and graph retrieval
- Verified versus inferred node labeling
- Saved investigative threads and filters
04
Human-AI Teaming Systems
Orchestrated AI assistance with human judgment in the loop. A delegation contract constrains what the AI is allowed to do, and database-level phase gates enforce it. Built for learning environments and decision-critical work where the AI must help but never decide.
Proof: Georgetown SEST
- Agent orchestration across fast, deep, and QA tiers
- Delegation contract constraining AI authority
- Database-enforced phase gates
- Voice and text surfaces, instructor tooling
Different problems, different infrastructure. Each engagement ends with a working system your team runs, not a document your team files.
Industries
Service Areas
Tech Transfer | R&D Decisions
Portfolio decisions in tech transfer are inherently high-uncertainty. You can't predict which bets will pay off, but you can make them systematically, document your reasoning, and move faster than the backlog allows.
Explore capabilitiesDefense & National Security
Competitive assessment demands synthesis across military, economic, and technological domains over long time horizons. Traceable reasoning. Explicit assumptions you can challenge, test, and refine.
Explore capabilitiesPolicy & Research Funding
Research outcomes are diffuse, long-term, and hard to attribute. Traceable pathways from funding to real-world impact, with evidence that holds up to auditors, oversight, and the press.
Explore capabilitiesInfrastructure & Public Risk
The work is triage, not perfection. You prioritize, document the reasoning, and leave a trail so that when regulators, elected officials, or the public ask questions, the answer is on the record.
Explore capabilitiesHealthcare & Biomedical Research
Clinicians don't need more alerts or dashboards. They need to know what changed, why it matters, and where to verify. Delivered where care happens, not in another system to check.
Explore capabilitiesCustom Decision Systems
Some decisions don't fit a playbook. When the stakes are high and off-the-shelf doesn't work, we build around the decision itself: who owns it, what evidence it requires, who will scrutinize the outcome. Human judgment stays in the loop. The reasoning stays visible. Your data stays yours.
Explore capabilities“
“Every system we build has to survive the moment someone asks how do you know. That's the whole business.”
Caleb Smith
Founder & CEO
Our Approach
How an engagement runs.
01
Scope
Before any building starts, we want to know exactly which decision the system has to support, who owns it, and what they will be asked when the decision goes wrong. The wrong scope produces an impressive demo nobody uses. We have walked away from engagements at this stage when the answers came back too vague.
02
Build
The architecture follows from the scope. A research funder gets a bibliometric pipeline against the portfolio. An archive gets a knowledge graph over the corpus. A competitive-assessment team gets the full eleven-stage workflow with provenance lineage end to end. We have built each of these, on real data, for real clients.
03
Hand off
The engagement ends when your team is running the system without us. We document the pipelines, train your operators, and stay close enough by phone to fix anything broken in the first month. After that, the system is yours, the data is yours, and the decisions made on top of it are yours.
FAQ
Questions From Leaders Who've Been Here Before
These are the questions that come up when we talk to leaders who've seen enough vendor pitches to be skeptical. They're worth asking of anyone in this space, including us.
AI projects often fail because they're framed as technical projects when they're actually organizational change projects. Someone buys a platform, a team builds models, the models perform well on test data, and then nothing changes. The decisions get made the same way they always did, by the same people, using the same inputs. The AI sits on the side, technically functional and organizationally irrelevant.
The usual culprit is starting from the wrong end. "We have all this data, what can we do with it?" is a recipe for building impressive demos that don't matter. So is "leadership wants an AI initiative." These projects optimize for what's measurable by technologists, like model accuracy, processing speed, and data coverage. Decision-makers care about whether they can trust an output, explain it to their boss, and defend it when something goes wrong. F1 scores are not on that list.
We start from the other end. A specific decision that matters, made by specific people, who answer to specific stakeholders. What evidence do they need? What does defensible look like in their world? Where does their current process break down? The technical architecture follows from those answers, not the other way around.
This is less exciting than a general-purpose AI platform. It's slower to show results in a demo. But it's the difference between a system that gets used and a system that gets abandoned.
Initiate Contact
Bring us a decision you have to defend.
Tell us about the decision you're trying to improve. We'll schedule a briefing with our principals to understand your environment and see whether the fit is right.
Schedule a briefing