back_office_ops · saas · workflow

Teads lets AI agents orchestrate ML experiments via Datakinator MCP, yielding 5–10% model uplift and nearly $1M in margin gain

Even after Datakinator gained a UI, manually adding features or choosing hyperparameters still took several minutes and left room for human error; earlier, the platform required launching a Scala notebook on the cloud that took up to 15 minutes each time, limiting the team to a few hundred experiments a year.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Data scientist triggers agent
The coding agent handles boring experiment-configuration tasks for data scientists.
Tools used
DatakinatorMCPcoding agent
Outcome

After enriching the MCP with context tools and adding cost guardrails, the agent enabled over 200 experiments in 48 hours, delivered up to a 5–10% uplift on offline metrics across multiple models, and translated to nearly a million in direct margin gain.

What failed first

The first agentic iteration relied only on existing API routes without enriched context, causing failures such as using the wrong date and referencing features that did not exist in specific datasets.

Results
Time savedmore than 200 experiments
Volume5–10%
Cost replaced$1M ROI
Source

https://medium.com/teads-engineering/we-let-ai-agents-orchestrate-our-ml-experiments-fc8606816fde

How we source this →

Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
agentic workflowai agentbuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementemployee productivityrevenue increasethroughput increasetechnical build writeupback office opsagentic task execution