[Blog](https://brainbaselabs.com/blog) / [Case study](https://brainbaselabs.com/blog?topic=case-study) Sep 4, 2026·[Case study](https://brainbaselabs.com/blog?topic=case-study) # Automating Domino's local competitor pricing research Cole Patterson · Member of Deployment Staff · 6 min read Domino's is the world's largest pizza company, with more than 22,500 stores across over 90 markets and a business built around delivery and carryout. Within Domino's CMO office, local competitor pricing analysis is a recurring market intelligence workflow. The team needs to understand how competitor prices vary across markets, stores, ordering channels, delivery modes and discounts. Brainbase benchmarked an agentic workflow to automate this process: collecting competitor prices, applying market-specific rules, filling the pricing workbook and routing exceptions for human review. 97% Final benchmark accuracy 52% Lower cost per source 41 min Faster turnaround per run Accuracy against cost per source Each point is one agent version, scored by manual review. The line steps along the Pareto frontier: each version on it was cheaper and more accurate than the last. Greyed versions fell back on one axis and sit off the line. Cost per source is the cleanest spend metric because the number of sources changed between runs; cheaper runs sit further right. ## The problem Competitor pricing research is highly manual because the “right” price depends on local context. A human analyst has to check competitor websites, delivery platforms and app-like ordering flows; select the correct location; compare delivery and takeaway pricing; identify the cheapest qualifying item; account for promotions or unavailable products; and then transfer the result into a customer workbook. The work is repetitive, but it is not simple. A wrong market, store, channel, promotion or menu assumption can make an otherwise completed source inaccurate. > “Competitor pricing is highly local, and small details matter. Brainbase helped us handle more of that complexity in a structured, repeatable way.” The core challenge: Domino's needed a faster and more repeatable way to collect local competitor pricing without losing the judgment required for edge cases. The metrics that mattered were accuracy, cost per source, average runtime, and whether discount search could be automated at all. ## The agent workflow Brainbase built an agent to automate the recurring collection process. The agent reads the target list, navigates competitor ordering surfaces, checks the correct local store or market, interprets delivery and takeaway pricing, identifies relevant promotions, fills the pricing workbook and flags exceptions for human review. 1. Target list 2. Local browsing 3. Price interpretation 4. Workbook fill 5. Human review The agent converts a manual browsing workflow into a repeatable pricing collection process. ## The benchmark The benchmark tracked multiple agent runs over time. Each run became a data point for measuring quality, cost and operational progress. For each run, we tracked: Measurement Why it matters Accuracy Measures output quality Runtime Measures turnaround speed Brainbase credits Measures total compute spend Dollars per run Converts credits into business cost Dollars per minute Shows run intensity Cost per source Normalises cost across changing scope Run notes Explains what changed between versions This made the project measurable as an iteration loop, not just a one-time automation demo. ## Accuracy improved across versions Accuracy by version Manual-review accuracy for each agent version. The dip at v10 came from a run with an incomplete corrected workbook; v11 recovered on the same playbook. The agent improved as each run exposed new edge cases and failure modes. Accuracy increased from 41% to 97% across the benchmark period. The largest improvements came from making the playbook more specific: better location matching, clearer delivery and takeaway handling, stronger discount logic, and more explicit rules for unavailable stores or ambiguous menu items. Improvement area Example change Location matching More explicit store and market checks Channel handling Clearer distinction between delivery and takeaway Promo logic Better treatment of discounts, vouchers and app-only campaigns Gap handling Cleaner treatment of unavailable stores or missing items Workbook completion More structured output and fewer blank fields ## Cost efficiency improved Cost per source is the cleanest spend metric because run scope changed over time. Across the benchmark, cost per source decreased from $2.11 to $1.01, a reduction of approximately 52%. This matters because competitor pricing is recurring work. Lower cost per source means the workflow can scale to more locations, markets and competitors without scaling manual effort at the same rate. ## Human work shifted from collection to review The manual workflow took at least two hours per run. The agent averaged approximately one hour and nineteen minutes, reducing elapsed turnaround by about 41 minutes per run. Agent runtime against the manual baseline Minutes per run. The dashed line is the manual workflow at its fastest, two hours. The agent averaged 1 hour 19 minutes across the benchmark. The largest change was the type of work being done. Before Brainbase, the human analyst had to manually collect every data point. After Brainbase, the agent handled the repetitive collection work while the human focused on reviewing exceptions, correcting edge cases and improving the next run. ## The improvement loop Each run created feedback that improved the next version. 1. Agent run 2. Agent review 3. Corrections 4. Playbook update 5. Better next run This loop was especially important because competitor pricing includes judgment-heavy edge cases: promotions, unavailable stores, local menu differences, channel-specific prices and source-specific quirks. The system improved because human corrections were converted into more specific playbook rules. ## Why it matters Brainbase gave Domino's a more repeatable way to monitor competitor pricing. The value is not only that one workbook can be completed faster. The value is that the workflow becomes measurable, reviewable and improvable over time. > “What stood out to me was the improvement loop. Each run surfaced issues, and those learnings made the next version more accurate.” - Faster competitive visibility - Lower cost per pricing source - More consistent methodology - Less repetitive manual analyst work - Better handling of local pricing complexity - A workflow that improves with each run ## Methodology notes This benchmark reflects an iterative operational pilot. Accuracy was estimated through manual review. Some runs did not have corrected workbooks available. Run scope changed across versions, so cost per source is more useful than total cost alone. Future versions should track manual review time, correction count, coverage rate and cost per completed pricing cell. Brainbase converted Domino's competitor pricing research from a manual recurring task into a repeatable agent workflow. Across the benchmark, the agent improved accuracy, reduced cost per source, shortened turnaround time, and created a feedback loop where human review made each subsequent run stronger. ## Related posts [Sep 3, 2026·Model release @openai/gpt-6-astra is live on Brainbase Brainbase Team · 6 min read](https://brainbaselabs.com/blog/openai-gpt-6-astra-live-on-brainbase) [Sep 2, 2026·Model release @meta/muse-spark-1.3 is live on Brainbase Brainbase Team · 5 min read](https://brainbaselabs.com/blog/meta-muse-spark-1-3-live-on-brainbase) [Sep 2, 2026·Model release @google/gemini-3.8-flash is live on Brainbase Brainbase Team · 5 min read](https://brainbaselabs.com/blog/google-gemini-3-8-flash-live-on-brainbase) [Sep 1, 2026·Model release @anthropic/claude-fable-5.1 is live on Brainbase Brainbase Team · 6 min read](https://brainbaselabs.com/blog/anthropic-claude-fable-5-1-live-on-brainbase) [Aug 26, 2026·Model release @zai/glm-5.3-flash is live on Brainbase Brainbase Team · 5 min read](https://brainbaselabs.com/blog/zai-glm-5-3-flash-live-on-brainbase) [Aug 12, 2026·Announcement Introducing Universal Managed Agents API Gokhan Egri · 7 min read](https://brainbaselabs.com/blog/universal-managed-agents) [Aug 12, 2026·Model release @spacexai/grok-4.6 is live on Brainbase Brainbase Team · 5 min read](https://brainbaselabs.com/blog/spacexai-grok-4-6-live-on-brainbase) [Aug 12, 2026·Model release @meta/muse-spark is live on Brainbase Brainbase Team · 5 min read](https://brainbaselabs.com/blog/meta-muse-spark-live-on-brainbase) [Jul 15, 2026·Model release @thinking-machines/inkling is live on Brainbase Brainbase Team · 4 min read](https://brainbaselabs.com/blog/thinking-machines-inkling-live-on-brainbase) [Jul 7, 2026·Announcement Brainbase is now generally available Gokhan Egri · 7 min read](https://brainbaselabs.com/blog/brainbase-is-now-ga) [View more posts →](https://brainbaselabs.com/blog)