Opportunity data was scattered
Tenders, procurement notices, and investment projects were published across separate federal and provincial sources. Users had to search each source independently.
Manifold Growth Partners built one searchable gateway to Canadian opportunities with Gyde
Canadian opportunity discovery
Users can search investment projects, tenders, and procurement notices collected from Canadian sources in one portal.
AI-assisted classification
Anthropic’s Claude models organize records by sector, province, and opportunity type, with uncertain records sent for review.
User and admin workspaces
Users can save searches and alerts, while admins manage sources, review records, and control what gets published.
About the client
About Manifold Growth Partners Inc.
Manifold Growth Partners is a quantitative investment firm that helps investors optimize their portfolios for consistent returns, independent of conventional market trends.
Manifold wanted to create a simpler way for global investors and companies to discover opportunities in Canada. The information they needed was scattered across federal, provincial, and municipal sites with no shared format.
Manifold brought in Gyde to build the discovery layer that made that diversification workable: one platform where investors could find, filter, and get alerted to Canadian opportunities that matched their sector and risk profile.
The problem statement
Finding the right Canadian opportunity took too much manual work
Large databases created more noise
Provincial registries contained thousands of projects, many of which did not match Manifold’s investment and supply objectives.
Source data was inconsistent
Dates, province names, sector labels, encodings, and record structures varied across sources, making reliable searching difficult.
Users and admins needed different controls
Investors and suppliers needed simple search and alerts. Admins needed source management, review queues, and control over publication.
How Gyde solved it
A reviewed AI workflow for finding opportunities in Canada
Defined which opportunities belonged in the portal
Manifold and Gyde agreed on the types of investment projects, tenders, and procurement notices that global investors and companies needed to find.
Connected and prepared Canadian data sources
A nightly worker collects new records from the connected sources, corrects inconsistent dates and province labels, and sorts notices by date before processing them. It also skips unchanged records, keeping older data from repeatedly entering the AI workflow.
Removed projects outside the target scope
Two provincial registries contained 2,249 projects. Filtering for industrial, infrastructure, and energy projects above $50 million narrowed these to 332 targeted listings rather than filling the portal with unrelated projects.
Used Claude where it could add value
Gyde uses Anthropic’s Claude models for different tasks: Haiku for routine classification, Sonnet for a second opinion on ambiguous records, and Opus for drafting summaries and newsletters. The AI helps organize information; it does not decide what gets published.
Put an administrator between AI and publication
Administrators review the suggested sector, province, opportunity type, and summary. They can approve, edit, or reject a record before users see it.
Built the portal around each user’s job
Investors and suppliers can search, filter, save, and share opportunities through links that preserve their chosen filters. Administrators have a separate workspace to manage sources, reviews, interests, alerts, and published listings.
The outcome
A working pipeline, built to stay accurate as it scales
Checking a dozen-plus government and agency sites by hand
One platform, personalized alerts, role-based access for investors and admins
17,000+ lines of TypeScript across six packages
No consistent way to verify a listing's classification before acting on it
Every listing re-validated against its schema, then reviewed by a person before it publishes
174 tests, including migrations run against a database
Processing cost that would grow with the size of the whole corpus
Cost tied to new or changed content only, via the hash-and-skip step
~$60/month estimated for classification at current volumes
The pattern behind the result
What it takes to make public opportunity data useful
Classification determines discoverability
A record placed in the wrong sector can become invisible to the person looking for it. Classification quality directly affects whether users find useful opportunities.
Human review protects trust
AI organizes and summarizes records, but administrators control publication. Thin, ambiguous, or low-confidence records remain in the review queue until someone checks them.
Taxonomy changes affect the whole product
Moving from 22 sectors to 13 required updates across listings, prompts, filters, user interests, alerts, and saved searches. Retain older sector codes as tags so you don't lose previous information.
In their words
What Manifold Leadership Says
We did not want to put more listings in front of people. We wanted investors and suppliers to find Canadian opportunities that matched what they were looking for. Gyde helped bring information from scattered sources into one portal and make it easier to search. It gives us a foundation we can expand as we connect more sources.
Rita Achrekar
Co-Founder at Manifold Growth Partners
85%
Less registry noise after narrowing 2,249 projects to 332 relevant opportunities
Nightly
Current Canadian opportunities prioritized over stale listings
100%
Of published AI-classified listings pass administrator review
Explore more success stories
More enterprises running Gyde in production
How Accounti Cut Onboarding Time for Investors by 33%
Read the full story →︎Tossit deploys a skill-verification system to assess cook capability
Read the full story →︎Have a valuable workflow buried in scattered data?
Gyde can help you turn it into a focused AI system with clear data sources, review rules, model choices, and a practical production boundary.