All services: Design · Build · Automate · Support

What We Do overview
  • Our process

    Five steps from idea to a product that keeps improving.

  • Engagement models

    Spec & quote projects, an agile retainer or team augmentation.

  • Our tools

    The playbook, CMS and project tools we built and use every day.

Who We Help overview
  • Company

    A boutique digital agency in Cedar Grove, NJ, since 2001.

  • What We Believe

    What we believe and how it shapes the way we work.

  • Team

    Meet the designers, developers and strategists.

  • Testimonials

    What our clients say about working with us.

  • Insights

    Ideas on software, AI and agents from our team.

All case studies Collaborative Content Management · News & Media

A newsroom workspace where reporters and AI work the same story

A broadcast media group needed one planning workspace for its TV newsrooms — and a way to plug AI into it without losing editorial control.

Industry
News & Media
Engagement
Backend, frontend & mobile
Cloud
AWS
Users
TV station newsrooms

Services provided

  • Platform Engineering
  • Real-Time Collaboration
  • AI Automation
  • Agent Integration (MCP)
  • AWS Deployment

The challenge

Newsrooms juggle stories, assignments, scripts, media and rundowns across tools that don’t talk to each other. Meanwhile the organization was building its own AI agents — and needed somewhere for them to do useful work, safely, inside the editorial workflow.

What we built

We built the newsroom planning platform: stories with assignments, tasks, comments and attachments; real-time collaborative script editing; rundowns and publishing.

Then we built the AI layer around it. Uploaded footage is transcribed automatically and turned into a draft story with a title and summary; stories are tagged from each station’s own tag list. And an MCP server and agent adapter let the client’s own agent platform read newsroom context and send its work back for a person to approve.

How it works

  1. 01

    Plan

    Stories, assignments and tasks are planned together across the newsroom.

  2. 02

    Write together

    Scripts are edited live by multiple people at once.

  3. 03

    Automate the busywork

    Footage is transcribed and drafted into a story; tags are suggested from the station’s own taxonomy.

  4. 04

    Bring in agents

    Through MCP tools, the client’s agents can read station context, the weekly overview, the team and stories.

  5. 05

    Approve

    Agent output comes back into the workspace for an editor to accept — never straight to air.

Pete Czech, CEO and founder of NP Group
Guardrails · 3 built in

Where people stay in charge

  • Agent output is always shown for human approval before it is used.

  • Agents read newsroom context through a defined set of tools, not open database access.

  • Script approvals notify the right people at the right time.

Sebastien Jean-Baptiste, Director of Product & Design at NP Group
Results · 3 outcomes

What changed

  • One planning workspace across stations — web and mobile.

  • Transcription and story drafting from uploaded media, automatically.

  • A standard way (MCP) for the client’s own AI agents to work inside the newsroom.

Technology

Built with

  • AWS
  • OpenAI
  • Laravel
  • PHP
  • PostgreSQL
  • Docker
Next case study Skills-Based Job Matching Nonprofit Matching people to jobs on what they can do, not the keywords they used
Pete, CEO and founder of NP Group

Pete CEO & Founder

Have a workflow like this? Let’s prove it with code.

Tell us the process that costs your team the most. In a few weeks we’ll show you, with working software against your own data, what agents and good design can do with it.