Skip to content
PROGRAM 30 · TEAM TRAINING

AI & Data for Media & Journalism Professionals

Research faster, verify better, and publish across every platform.

Important: AI helps with research and production, never with inventing facts. Every claim, quote and figure must be verified against real sources before publishing, and AI-generated images are never presented as news photographs.

8 sessions3 modules4 hands-on projects3 days · 9 am–5 pmCertificate on completion
CHOOSE A FORMAT
Request a proposalSee the curriculum

Who this course is for

  • Reporters, sub-editors and news editors
  • Digital desk, social media and video teams
  • Researchers, fact-checkers and data journalists
  • Teams in national dailies, online portals, TV newsrooms and YouTube news channels

What your team will be able to do

  • Build background briefs and timelines quickly, with every fact sourced
  • Turn interviews and press conferences into transcripts, quotes and drafts
  • Repurpose one story for web, social, video and newsletter
  • Deploy four working automations for your newsroom
How it runs

3 days at your office, 8 sessions

Three sessions a day plus a hands-on build lab every afternoon. Day 3 ends with capstone presentations.

Day 1

9:00 am – 5:00 pm

AI chatbots for newsroom work

9:00–10:30S1Prompt engineering for media
10:30Tea break
10:45–12:15S2Research, interviews & verification
12:15Lunch & prayer
1:00–2:30S3One story, every platform
2:45–4:30LABBuild lab: prompt library on your own files
4:30–5:00Q&A and day recap

Day 2

9:00 am – 5:00 pm

Data stories, then the first two builds

9:00–10:30S4Formulas & newsroom data cleaning
10:30Tea break
10:45–12:15S5Data journalism & audience analytics
12:15Lunch & prayer
1:00–2:30S6Projects 01 & 02: Assistant & alerts
2:45–4:30LABBuild lab: data story, assistant and alerts on your data
4:30–5:00Q&A and day recap

Day 3

9:00 am – 5:00 pm

Last two builds and the capstone

9:00–10:30S7Project 03: Pitch & edit approval
10:30Tea break
10:45–12:15S8Project 04: Press release extraction
12:15Lunch & prayer
1:00–3:00LABCapstone build clinic
3:15–4:30LABCapstone presentations
4:30–5:00Certificates and next steps
Group: 10–40 people from one organisationSame content and projects in both formatsBangla delivery with English technical termsEvery session ends with a deliverable
Curriculum

8 sessions, one build in each

3 modules · 8 sessions · 4 hands-on projects

PART 1AI Chatbots for Media WorkSessions 1–3

Chatbot Landscape & Tool Selection

  • Gemini, ChatGPT, Claude, Copilot and DeepSeek: strengths for media work (Bangla and English drafts, long document summaries, transcript work, data tables)
  • Free vs paid tiers; a workflow that needs no international payment card
  • Bangla vs English output quality; when to draft in English and translate
  • Which tool for a long document, which for a formula, which for a polished letter

Prompt Engineering Fundamentals

  • What a prompt is; why the same question gives different answers
  • The four-part structure: role, context, task, output format
  • Role prompting: act as a reporter, sub-editor, fact-checker or digital news producer
  • Controlling output: length, tone, language, table or bullet format

Advanced Prompting Techniques

  • Few-shot prompting: teaching the model with examples of your own media work
  • Step-by-step reasoning for multi-part tasks such as building a timeline from several reports that give different dates and figures
  • Constraint prompting: what to include, what to exclude, what to never assume
  • Chained prompts: breaking a story package (background → interview notes → draft → headlines → social versions) into a sequence of smaller steps

Iteration & Prompt Library Building

  • Why the second prompt matters more than the first; refining instead of restarting
  • Diagnosing a bad output: vague instruction, missing context or wrong tool
  • Building reusable prompt templates for repeated media tasks
  • Testing a prompt before it goes into daily use

Data Privacy & Verification Discipline (Core)

  • What must never be pasted: confidential source names and contacts, unpublished investigations, leaked documents, embargoed material, staff passwords
  • Anonymising data before prompting; safe vs unsafe media use cases
  • Hallucination awareness; verifying every figure, date, name and legal reference
  • The verification rule: AI drafts, a person checks before anything leaves the building
DELIVERABLEa personal prompt library of 10 templates for your repeated media tasks.
PART 2Media Data Analysis in Excel & Google SheetsSessions 4–5
PART 3Applied Projects: AI Assistants & AutomationSessions 6–8
Applied projects

Four automations, running in your organisation

01Session 6

Newsroom Style & Ethics Assistant

Reporters, sub-editors and new joiners get answers from the house style guide, editorial policy and corrections policy, with the section cited.

  1. INStyle guide & editorial policy
  2. AIGrounded Gemini assistant
  3. OUTAnswer with the section cited
Built with Google AI Studio
02Session 6

Newsroom Deadline & Renewal Alerts

Accreditation expiries, embargoes, court dates, licence renewals and right-of-reply deadlines checked daily, with alerts 30, 15 and 7 days ahead.

  1. INDeadline & renewal tracker
  2. RUNDaily Make scenario
  3. OUTAlert to the right owner
Built with Make · Sheets · Gmail
03Session 7

Story Pitch & Edit Approval Workflow

Pitches routed to the desk editor, high-risk stories sent for legal or senior review, and approved stories added to the story budget.

  1. INStory pitch form
  2. RULESPitch routing script
  3. OUTApproved story with an owner
Built with Apps Script · Forms
04Session 8

Press Release & Document Extraction

Press releases, notices and court orders become clean rows, grouped by beat, with figures that differ from the previous release flagged.

  1. INReleases, notices & circulars
  2. AIGemini structured extraction
  3. OUTRows sent to the right desk
Built with Gemini API · Drive

Capstone presentation

Each person presents one automation built for their own workplace.

Day 3 afternoon
Applied across every session

Responsible & Ethical AI in Media

Fairness & Non-Discrimination

  • Where bias enters media decisions: data, wording, criteria and past patterns
  • Proxy discrimination: address, age, gender or background inferred indirectly

Privacy & Data Protection

  • Data minimisation: collect only what the decision requires
  • Retention and deletion of source, interviewee and reader data

Accuracy, Attribution & Public Trust

  • Disclosing AI use to readers where your policy requires it
  • Never fabricating quotes, sources, images or eyewitness accounts

Accountability & Human Oversight

  • Human-in-the-loop by design: AI recommends, a named person decides
  • Who owns an AI-assisted decision when it is challenged

Workforce Impact & Your AI Use Policy

  • Talking to media teams about AI without triggering job-loss fear
  • Reskilling and role redesign as AI absorbs routine work
Outcomes

By the end, your team can

  • Choose the right AI tool and write prompts that work first time
  • Maintain a prompt library covering your repeated media tasks
  • Research and verify faster, with a source for every fact
  • Turn one story into web, social, video and newsletter versions
  • Clean public data and build honest charts for data stories
  • Build and deploy automations with Make, Apps Script and the Gemini API
  • Apply fairness, transparency and privacy to every AI-assisted decision

And leaves with

A research brief template and a verification log
A story repurposing kit with headline and video script prompts
A data story with verified charts and an audience performance summary
A grounded newsroom style & ethics assistant your colleagues can use
A newsroom deadline & renewal alert engine that reaches the right owner
Four deployed automations running in your own organisation
A written AI use policy for your own newsroom

Tools your team will use

Chatbots
ChatGPTGeminiClaudeCopilotDeepSeek
Content
CanvaGammaCapCutGoogle Slides
Data
Microsoft ExcelGoogle SheetsPower Query
Workspace
GmailCalendarMeetFormsDrive
Automation & AI builds
MakeGoogle AI StudioApps ScriptGemini API
Media tools
PerplexityDatawrapperreverse image searchtranscription tools

What participants need

  • A laptop with Excel and a Google account
  • Basic Excel comfort and one recent story, interview or public dataset to work with
  • One real work file to practise on from Session 2
  • No coding background required; free tiers only

How your team will learn

  • build-along classes (you work while the trainer works)
  • practise on your own workplace file, not dummy data
  • every session ends with a deliverable
  • Bangla delivery with English technical terms
  • recordings, prompt library and setup guides
  • certificate after capstone submission
Request a proposal

Bring this program to your newsroom

Tell us about your team. We reply within one working day with a plan built around your own documents and workflows.

  1. 1 · A short discovery call with your newsroom lead
  2. 2 · We tailor examples to your masked files
  3. 3 · Offline at your office, or online live classes
Chat on WhatsApp
Request a proposal