Marketing ops · Production

How Guidesly built AI-generated trip reports for outdoor guides on AWS

The problem

Outdoor guides spent up to eight hours a day on marketing tasks—writing trip reports, updating websites, posting to social media, and running email campaigns—leaving little time for guiding clients. Manual content creation lacked authenticity at scale, missed SEO opportunities, and could not keep pace with client demand.

Workflow diagram · grounded in source
1
Trip media upload
trigger
“Trip photos and videos uploaded by guides to enter the system through Amazon API Gateway, which immediately triggers the orchestration pipeline.”
2
Metadata extraction and enrichment
integration
“The extracted geospatial information is then combined with relevant weather and water condition data for the same time and location. This captures details such as tide levels, water temperature, wind speed, and cloud cover—context that w…”
3
Fish detection and classification
ai_action
“we designed a multilayer computer vision pipeline that combines custom-trained computer vision models with foundation vision models available through AWS services”
4
Tone calibration via reference retrieval
ai_action
“historical trip reports and guide-specific phrasing patterns are retrieved and included as reference examples. This helps the model mirror the vocabulary, pacing, and descriptive style that guides naturally bring to documenting their trips”
5
Content generation via Amazon Bedrock
ai_action
“Generation itself is executed using Amazon Bedrock FMs, which process the contextual inputs and structured prompts to produce coherent, domain-appropriate reports at scale”
6
Guide review and approval
human_review
“Guides can review and approve generated content, request refinements, or rely on a built-in auto-publish toggle for full automation”
7
Multi-channel asset publishing
output
“This includes SEO-friendly trip reports, fresh website content, social media posts, and personalized email campaigns”
Reported outcome

Jack AI automated marketing tasks that previously took guides more than six hours every week, reduced asset generation time from 13 minutes in December 2024 to two minutes by August 2025, scaled content output from under 800 assets in early 2025 to more than 2,500 by midsummer, and helped the five most active guides grow average monthly revenue from approximately $3,000 to more than $27,000—a nearly 9× increase in six months.

Reported metrics
Daily marketing time pre-automationup to eight hours a day
Weekly marketing time pre-automationmore than six hours every week
asset generation time (December 2024 baseline)13 minutes
asset generation time (August 2025)two minutes
Show all 13 reported metrics
daily marketing time pre-automationup to eight hours a day
weekly marketing time pre-automationmore than six hours every week
asset generation time (December 2024 baseline)13 minutes
asset generation time (August 2025)two minutes
monthly reports generated (early 2025)just over 100 reports
monthly reports generated (July 2025)nearly 340 reports
content assets (early 2025)under 800 assets
content assets (midsummer 2025)more than 2,500
avg monthly revenue, top 5 guides (January 2025)approximately $3,000
avg monthly revenue, top 5 guides (July 2025)more than $27,000
revenue increase, top 5 guides (6 months)nearly 9× increase in just six months
cost per trip report$0.10 to $0.50 per report
fish species classes supportedover 400 fish species classes
Reported stack
Amazon API GatewayAWS Step FunctionsAWS LambdaAmazon S3Amazon RDSAmazon SageMaker AIAmazon BedrockJupyterLabYOLO
Source
https://aws.amazon.com/blogs/machine-learning/how-guidesly-built-ai-generated-trip-reports-for-outdoor-guides-on-aws/
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Jack AI automated marketing tasks that previously took guides more than six hours every week, reduced asset generation time from 13 minutes in December 2024 to two minutes by August 2025, scaled content output from un…

What tools did this team use?

Amazon API Gateway, AWS Step Functions, AWS Lambda, Amazon S3, Amazon RDS, Amazon SageMaker AI, Amazon Bedrock, JupyterLab, YOLO.

What results were reported?

Daily marketing time pre-automation: up to eight hours a day; Weekly marketing time pre-automation: more than six hours every week; asset generation time (December 2024 baseline): 13 minutes; asset generation time (August 2025): two minutes (source-reported, not independently verified).

How is this marketing ops AI workflow structured?

Trip media upload → Metadata extraction and enrichment → Fish detection and classification → Tone calibration via reference retrieval → Content generation via Amazon Bedrock → Guide review and approval → Multi-channel asset publishing.

Related marketing ops cases