AI & Intelligence

AI that knowsyour agency

Groq-powered conversational AI, 8 anomaly analyzers, semantic search, and fine-tuned models -- all trained on your agency data.

Conversational AI

Ask questions about your clients, campaigns, budgets, and workflows in plain language. Mention any entity with @client, @task, or @project to pin context directly into the conversation.

The AI understands your agency's structure -- it retrieves relevant tasks, briefs, spend data, and timesheets to give you answers grounded in real data, not hallucinations.

Groq LLM

Ultra-fast inference powered by Groq. Sub-second responses for real-time conversational workflows.

@Entity Mentions

Type @client, @task, or @project to pin entities into context. The AI fetches their full data automatically.

Context Awareness

Intent classification routes queries to the right data sources -- spend, timesheets, tasks, briefs, or knowledge base.

Conversation Pinning

Pin important conversations for quick access. Up to 25 pinned threads per user with dedicated sidebar section.

Rate Card Queries

Ask pricing questions in plain language. Rate card entries are embedded in the vector database so the AI knows your exact service rates.

Time Tracking Queries

Ask "How many hours on Client X last month?" and get instant answers. Timesheet gap analysis spots missing entries automatically.

8 specialized analyzers

A proactive agent that continuously scans your agency data and flags issues before they become problems.

Spend Anomaly

Detects unusual spikes or drops in ad spend across Meta and Google campaigns.

Budget Overrun

Flags campaigns approaching or exceeding their monthly budget limits.

Deadline Risk

Identifies tasks and projects at risk of missing their due dates.

Client Health

Monitors client engagement signals and flags accounts needing attention.

Revenue Trend

Tracks revenue patterns and alerts on declining or stagnant client revenue.

Utilization

Analyzes team capacity and flags over- or under-utilized team members.

Campaign Performance

Evaluates campaign KPIs against benchmarks and flags underperformers.

Billing Gap

Finds unbilled work, missing invoices, and revenue leakage across clients.

Semantic Search

Powered by Cloudflare Vectorize, search goes beyond keyword matching. Find tasks, clients, briefs, and knowledge base entries by meaning -- not just exact text.

Every result is ranked by a 5-signal composite score that combines semantic similarity, recency, entity importance, intent match, and entity overlap. The system automatically diversifies results so you see the full picture, not just one type of match.

Semantic Similarity

Vectorize cosine similarity matches results by meaning, not just keywords.

Recency

Exponential decay scoring with configurable half-life per intent type.

Entity Importance

Weighted scoring by entity type -- spend data ranks higher than board metadata.

Intent Match

Edge-classified intent aligns results to what you are actually asking about.

Entity Overlap

Results mentioning the same clients, projects, or tasks as your query rank higher.

AI-Powered Briefs

AI assists at every stage of brief creation — from suggesting field values as you type, to scoring brief quality in real time, to generating complete briefs from a single paragraph.

The quality scoring engine rates each brief across three dimensions: required field completion (40%), optional fields (20%), and content quality (40%). Issues like vague language, conflicting requirements, and unrealistic timelines are flagged with specific improvement suggestions.

Field Suggestions

AI suggests values for empty fields as you type — target audiences, platforms, timelines — based on context and past briefs.

Brief Generator

Provide a one-paragraph description and AI populates every template field. Accept, edit, or reject each suggestion individually.

Quality Assessment

AI reviews completed briefs for vague language, conflicting requirements, and unrealistic timelines with specific fix suggestions.

Edge AI inference

Powered by Cloudflare Workers AI, intent classification and summarization run at the edge for sub-50ms latency with Groq fallback.

Intent Classification

Queries are classified at the edge into financial, process, search, time tracking, pricing, and other intents — routing to the right data sources in under 50ms.

Edge Summarization

Long documents and thread summaries are generated at the edge via Llama 3.1 8B. No round-trip to external APIs — everything stays on Cloudflare's network.

Graceful Fallback

If Workers AI is unavailable, requests automatically fall back to Groq for classification and generation. Zero downtime for AI features.

Fine-tune with your data

Train custom LoRA adapters on your agency's chat history, knowledge base, and workflows. Route traffic between adapters with weighted A/B testing.

Training Data Extraction

Five extractors pull chat Q&A pairs, intent examples, RAG documents, knowledge entries, and combined datasets. Automatic anonymization and JSONL export to R2.

Adapter Management

Upload, activate, and retire LoRA adapters. Weighted traffic routing lets you A/B test new models against the baseline with gradual rollout.

Metrics Dashboard

Track adapter performance across response quality, latency, and user satisfaction. Compare adapters side-by-side and promote winners automatically.

Intelligence built for agencies

Stop digging through dashboards. Ask the AI, and it finds the answer.

Get Started