Expert-built decision layer
Capability starts from expert decision logic captured in interviews and tightened through review, not from generic model summarisation.
Skillify Turning expert judgment into validated, reusable AI capability for investment workflows
For design partners who need AI-powered investment workflows shaped by validated expert judgment, not generic model output.
Selective design-partner engagement. Conversations stay relevant to your workflow and trust boundary.
Exploratory intro only. Booking does not create a contract, commitment, or commercial obligation.
What design partners get
A validated judgment layer for investment workflows, not another prompt pack.
The layer is reviewable and reusable inside a real investment workflow, with ownership and permissioning kept explicit.
Definition. Turning expert judgment into validated, reusable AI capability for investment workflows. Skillify captures decision logic from expert interviews, validates it with the expert, and deploys it where partners have agreed. It is not investment advice, trading signals, asset management, or automated trade execution.
Production AI skills
Judgment is packaged into triggers, decision logic, and workflow-ready behavior that can travel with the partner’s operating context.
Protected deployment
Expert IP and partner data stay permissioned. Nothing is publicly disclosed without approval, and use remains governed by agreement.
How Skillify works
One connected loop from expert interview to design-partner workflow.
Capture, expert review, then a permissioned partner workflow. The same loop is written out on how it works.
Expert cycle
Interview → validated skill
Real decision moments are compressed into reviewable skills the expert can check and keep attribution over.
Expert interview
We capture real cases, judgment calls, and the reasoning behind them.
Skill extraction
Skillify pulls out reusable decision logic, triggers, and edge-case handling.
Expert review
The strongest skills are tightened, clarified, and checked with the expert.
Validated skill
A private skill artifact is returned for expert review, with participation when approved skills are deployed in live Skillify workflows.
Validated judgment becomes reusable Skillify capability
Design partner cycle
Skill package → deployed workflow
The same skills move from expert-validated artifact into an agreed workflow used by a design partner.
Capability packaging
Skills are structured into logic and workflow-ready system behavior.
Design partner workflow
The capability is inserted into a real operating context rather than left as a memo.
Structured output
The partner gets AI workflow output shaped by an expert-built decision layer, not generic AI summarisation.
Feedback loop
New partner cases and expert review feed back into the system to improve the capability over time.
Expert-built skills
Validated judgment
Design partner deployment
Continuous learning loop
Why this matters
Generic AI can summarise. It does not reliably know what matters in edge cases.
Tacit judgment
The most valuable part of expert performance is rarely written down. It sits in pattern recognition, exception handling, and what gets weighted when conditions change.
What generic AI misses
Foundation models can restate the obvious. They are less reliable when the job is to notice which assumption just broke and how that should update the decision.
Why partners feel it
If expert judgment is not captured, validated, and kept usable as a skill, partner workflows stay fragile, expensive, and hard to trust where edge cases matter most.
Design partner engagement
A selective working relationship with clear expectations.
Intro call
5–15 minutes to confirm fit, workflow relevance, and whether a design-partner track is worth starting. Exploratory only: no contract or commitment implied.
Workflow scoping
Identify one concrete investment workflow where validated expert judgment would change output quality.
Capability pilot
Deploy a permissioned skill package into that workflow and review outputs against expert standards.
Feedback loop
Partner cases and expert review tighten the capability. Deeper involvement is possible, not assumed.
What partners influence
Real say over how capability is packaged and evaluated.
Shape the first skill packages
Help define how expert reasoning is structured for live partner workflows.
Set the evaluation bar
Push the system toward what matters in operating judgment, not generic model theatre.
Early access to capability
See how validated judgment translates into deployable tools inside an agreed investment workflow.
Protected collaboration
Work inside clear permissioning so expert IP and partner context stay governed.
“The days of people making decisions in their own heads are ending.”
Ray Dalio
Founder, Bridgewater Associates
“The vast majority of human knowledge is not expressed in text; it’s in the subconscious part of your mind.”
Yann LeCun
Chief AI Scientist, Meta
Together these capture Skillify’s thesis: more decisions are moving into systems, but the knowledge those systems need often lives in expert judgment rather than text alone.
Knowledge handling and trust
How expert knowledge and partner context are handled matters from the start.
Confidential by default
Interviews, case walkthroughs, partner context, and draft artifacts are treated as private unless a different agreement is made explicitly.
Provenance matters
We care about where a skill came from, how it was derived, and what confidence belongs around it.
Permissioned deployment
The goal is not extraction theatre. It is to structure expert judgment so it remains useful, reviewable, and only used where partners have agreed.
Public materials are illustrative. Skillify does not provide investment advice, trading signals, asset management, or trade execution. Expert IP and partner data stay permissioned. Full terms, privacy, and the disclaimer are on Legal.
Who is behind this
Built inside Blackkite Ventures.
Skillify is being developed within Blackkite Ventures as a focused effort around: Turning expert judgment into validated, reusable AI capability for investment workflows.
Gary Pratt
Founder
Former macro PM with 10 years of experience building and evaluating macro research processes, including at BFAM Partners and ExodusPoint.
Why this exists
The best workflows often depend on judgment that is real, valuable, and largely undocumented. Skillify is an attempt to preserve and operationalise that layer without pretending generic AI already solved it.
We are speaking with a small number of design partners now.
If your workflow depends on judgment that generic systems do not reliably capture, we would value the conversation. Common questions are on FAQ.
Exploratory intro only: no contract, commitment, or commercial obligation is implied by booking.