Peter Zhang
Mar 24, 2026 17:27
Moda’s Deep Brokers-powered platform allows non-designers to create production-grade visuals by a three-agent structure with customized DSL for format reasoning.
Moda has revealed the technical structure behind its AI-native design platform, showcasing a three-agent system constructed on LangChain’s Deep Brokers framework that lets entrepreneurs, founders, and small enterprise homeowners produce skilled shows and advertising and marketing supplies with out design experience.
The platform—positioned as a Canva various with Cursor-style AI help—addresses a elementary downside in AI-generated design: LLMs battle with visible layouts as a result of they’re horrible at reasoning about pixel coordinates.
Why PowerPoint’s DNA Breaks AI Design
Most design instruments depend on codecs like PowerPoint’s XML spec, which makes use of absolute XY coordinates to place components. “LLMs should not good at math,” stated Ravi Parikh, highlighting why AI-generated decks usually look generic and poorly composed.
Moda’s resolution? A proprietary domain-specific language (DSL) that provides the AI format abstractions reasonably than uncooked numerical coordinates—much like how Flexbox and CSS grid make net growth accessible to language fashions. The corporate is not sharing specifics, however the method reportedly cuts token prices whereas bettering output high quality.
Three Brokers, One Canvas
The system runs three specialised brokers:
Design Agent handles real-time creation and iteration by the AI sidebar. This runs on a customized LangGraph loop, although migration to Deep Brokers is beneath analysis.
Analysis Agent pulls structured content material from exterior sources like firm web sites, storing it in a per-user file system. Already working on Deep Brokers.
Model Package Agent ingests colours, fonts, logos, and model voice from web sites, uploaded tips, or present decks. Additionally Deep Brokers-powered.
All three share a typical structure: light-weight triage utilizing quick Haiku fashions, dynamic context loading, and full observability by LangSmith tracing.
The Context Engineering That Really Issues
Moda’s triage system classifies every request by output format—slide deck, PDF, LinkedIn carousel—then pre-loads related “expertise,” that are Markdown paperwork containing design finest practices and format-specific directions. Immediate caching breakpoints sit after the system immediate and expertise block, protecting frequently-used context cached whereas permitting dynamic injection.
The Design Agent maintains 12-15 core instruments in context, with roughly 30 extra instruments obtainable on demand by a RequestToolActivation name. Every further software prices 50-300 tokens and breaks immediate caching, however the information exhibits most requests do not want them.
For giant tasks—say, a 20-slide deck—the system dynamically manages context, offering high-level summaries and letting the agent pull particulars as wanted reasonably than loading all the pieces upfront.
Collaboration Over Technology
What separates Moda from typical AI design instruments is the interplay mannequin. As an alternative of generate-and-replace, the AI works immediately on a totally editable 2D vector canvas. Each factor stays selectable, movable, and styleable. The connection shifts from “settle for or reject” to real back-and-forth refinement.
The platform has reportedly discovered early traction with B2B firms doing enterprise gross sales—groups that want polished pitch decks quick however need management over the ultimate product. Integration with Microsoft 365 workflows provides enterprise enchantment.
What’s Coming
Moda’s roadmap contains finishing the Deep Brokers migration for the Design Agent, activating reminiscence primitives already in place, and increasing model context assist for multi-team enterprise prospects. Formal analysis techniques are deliberate however not but carried out—for now, LangSmith traces function the first suggestions mechanism for catching regressions.
The technical disclosure presents a helpful blueprint for groups constructing manufacturing AI brokers: customized context representations beat uncooked information codecs, dynamic software loading outperforms kitchen-sink approaches, and observability is not elective once you’re delivery to actual customers.
Picture supply: Shutterstock
